Coding techniques for neural network architectures.

Abstract

Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive an indication of one or more encoding operations to be used to encode a compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both. In some examples, using a neural network, the UE may first encode the data set based on an additional encoding operation to generate a compressed data set, and then quantize the compressed data set that is encoded based on the additional encoding operation. Subsequently, after the data set has been first encoded and then quantized, the UE may further encode and compress the data set using the indication of the one or more encoding operations. The UE may then transmit the data set to a second device based on the one or more encoding operations.

Description

[Technical field]

[0001] cross reference This patent application claims the benefit of U.S. patent application Ser. No. 17 / 194,077, entitled “ENCODING TECHNIQUES FOR NEURAL NETWORK ARCHITECTURES,” by Vitthaladevuni et al., filed March 5, 2021, and assigned to the assignee of this application.

[0002] The following relates to wireless communications, including coding techniques for neural network architectures. [Background technology]

[0003] Wireless communication systems are widely deployed to provide various types of communication content, such as voice, video, packet data, messaging, broadcasts, and the like. These systems may be capable of supporting communication with multiple users by sharing available system resources (e.g., time, frequency, and power). Examples of such multiple access systems include fourth generation (4G) systems, such as Long Term Evolution (LTE), LTE-Advanced (LTE-A) or LTE-A Pro systems, and fifth generation (5G) systems, sometimes referred to as New Radio (NR) systems. These systems may employ technologies such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal FDMA (OFDMA), or Discrete Fourier Transform Spread Orthogonal Frequency Division Multiplexing (DFT-S-OFDM). Summary of the Invention [Problem to be solved by the invention]

[0004] A wireless multiple-access communication system may include one or more base stations or one or more network access nodes, each simultaneously supporting communication for multiple communication devices, sometimes known as user equipment (UE). In some wireless communication systems, the UE may make some measurements of channel conditions as part of communicating with the base station. In some examples, these measurements may generate a large amount of data to be transmitted to the base station to assist the base station in network management. [Means for solving the problem]

[0005] The described techniques relate to improved methods, systems, devices, and apparatuses that support encoding techniques for neural network architectures. In general, the described techniques provide for a user equipment (UE) receiving an indication of one or more encoding operations to be used to encode a compressed data set, the one or more encoding operations including a differential encoding operation, or an entropy encoding operation, or both. In some examples, using a neural network, the UE may first encode a data set based on an additional encoding operation (e.g., a single-shot encoder) to generate a compressed data set, and then quantize the compressed data set that is encoded based on the additional encoding operation. Subsequently, after the data set is first encoded and then quantized, the UE may further encode and compress the data set using the indication of the one or more encoding operations. The UE may then transmit the data set (e.g., the encoded, quantized, and compressed data set) based on using the one or more encoding operations to a second device (e.g., a base station, an additional UE, etc.) to further encode the information after quantizing the data using the neural network. In some examples, the differential encoding operation may include encoding an amount of data (e.g., after an additional encoding operation) based on a previous value for that amount of data of the compressed data set, such as an initial value, an initial reconstructed value, a previous reconstructed value, a previous value for the same data from a previous time instance, etc.

[0006] A method for wireless communication in a UE is described. The method may include receiving an indication of one or more encoding operations to be used to encode a compressed data set, where the one or more encoding operations include a differential encoding operation or an entropy encoding operation or both, encoding the data set to generate a compressed data set by a neural network, quantizing the compressed data set encoded by the neural network, encoding the quantized compressed data set based on receiving the indication of the one or more encoding operations, and transmitting the encoded quantized compressed data set to a second device after encoding the compressed data set based on the one or more encoding operations.

[0007] An apparatus for wireless communication in a UE is described. The apparatus may include a processor, a memory coupled to the processor, and instructions stored in the memory. The instructions may be executable by the processor to cause the apparatus to receive an indication of one or more encoding operations to be used to encode a compressed data set, where the one or more encoding operations include a differential encoding operation or an entropy encoding operation or both, encode the data set by a neural network to generate a compressed data set, quantize the compressed data set encoded by the neural network, encode the quantized compressed data set based on receiving the indication of the one or more encoding operations, and transmit the encoded, quantized, compressed data set to a second device after encoding the compressed data set based on the one or more encoding operations.

[0008] Another apparatus for wireless communication in a UE is described. The apparatus may include means for receiving an indication of one or more encoding operations to be used to encode a compressed data set, where the one or more encoding operations include a differential encoding operation or an entropy encoding operation or both, means for encoding the data set to generate a compressed data set by a neural network, means for quantizing the compressed data set encoded by the neural network, means for encoding the quantized compressed data set based on receiving the indication of the one or more encoding operations, and means for transmitting the encoded quantized compressed data set to a second device after encoding the compressed data set based on the one or more encoding operations.

[0009] A non-transitory computer-readable medium storing code for wireless communication in a UE is described. The code may include instructions executable by a processor to receive an indication of one or more encoding operations to be used to encode a compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both, encode a data set by a neural network to generate a compressed data set, quantize the compressed data set encoded by the neural network, encode the quantized compressed data set based on receiving the indication of the one or more encoding operations, and transmit the encoded, quantized, compressed data set to a second device after encoding the compressed data set based on the one or more encoding operations.

[0010] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, receiving an indication of the one or more encoding operations may include acts, features, means, or instructions for receiving one or more parameters corresponding to the one or more encoding operations, each of the one or more parameters corresponding to a respective encoding operation of the one or more encoding operations, and the quantized and compressed data set may be encoded based on the one or more parameters.

[0011] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, encoding the quantized and compressed data set may include operations, features, means, or instructions for encoding the data set using a neural network and then encoding the quantized and compressed data set using a differential encoding operation.

[0012] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, encoding the quantized and compressed data set may include operations, features, means, or instructions for encoding the data set using a neural network and then encoding the quantized and compressed data set using an entropy encoding operation.

[0013] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, encoding the quantized compressed data set may include operations, features, means, or instructions for determining, after quantizing the compressed data set encoded by a neural network, a difference value between a first value of data in the quantized compressed data set at an initial time instance and a second value of the data at a second time instance after the initial time instance, where the difference value may be determined based on an indication of one or more encoding operations, and the quantized compressed data set may be encoded based on the difference value.

[0014] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, encoding the quantized compressed data set may include operations, features, means, or instructions for determining, after quantizing the compressed data set encoded by a neural network, a difference value between a first reconstruction value of data in the quantized compressed data set at a first time instance and a second reconstruction value of the data at a second time instance after the first time instance, wherein the difference value may be determined based on an indication of one or more encoding operations, and the quantized compressed data set may be encoded based on the difference value.

[0015] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, encoding the quantized compressed dataset may include operations, features, means, or instructions for determining, after quantizing the compressed dataset to be encoded by a neural network, an initial reconstruction value of data in the quantized compressed dataset at an initial time instance value associated with encoding the dataset, and determining, after quantization, a difference value between an additional reconstruction value of the data at an additional time instance after the initial time instance and the initial reconstruction value of the data, wherein the difference value may be determined based on an indication of one or more encoding operations, and the quantized compressed dataset may be encoded based on the difference value.

[0016] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the differential encoding operation may include encoding an amount of data of the compressed data set based on a previous value for that amount of data.

[0017] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the entropy encoding operation may include encoding the compressed data set using one or more symbols having lengths that vary based on the probability that the symbol occurs.

[0018] A method for wireless communication in a device is described. The method may include transmitting to a UE an indication of one or more encoding operations that the UE should use to encode a compressed data set, where the one or more encoding operations include a differential encoding operation or an entropy encoding operation or both, receiving from the UE an encoded, quantized, compressed data set after the compressed data set has been encoded following a quantization operation based on the one or more encoding operations, decoding the encoded, quantized, compressed data set to generate a compressed data set based on the one or more encoding operations, and decoding the compressed data set to generate a data set based on decoding the encoded, quantized, compressed data set by a neural network.

[0019] An apparatus for wireless communication in a device is described. The apparatus may include a processor, a memory coupled to the processor, and instructions stored in the memory. The instructions may be executable by the processor to cause the apparatus to send, to a UE, an indication of one or more encoding operations that the UE should use to encode a compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both, receive from the UE an encoded, quantized, compressed data set after the compressed data set has been encoded following a quantization operation based on the one or more encoding operations, decode the encoded, quantized, compressed data set to generate a compressed data set based on the one or more encoding operations, and decode the compressed data set to generate a data set based on decoding the encoded, quantized, compressed data set by a neural network.

[0020] Another apparatus for wireless communication in a device is described. The apparatus may include means for transmitting to a UE an indication of one or more encoding operations that the UE should use to encode a compressed data set, where the one or more encoding operations include a differential encoding operation or an entropy encoding operation or both, means for receiving from the UE an encoded, quantized, compressed data set after the compressed data set has been encoded following a quantization operation based on the one or more encoding operations, means for decoding the encoded, quantized, compressed data set to generate a compressed data set based on the one or more encoding operations, and means for decoding the compressed data set to generate a data set based on decoding the encoded, quantized, compressed data set by a neural network.

[0021] A non-transitory computer-readable medium storing code for wireless communication in a device is described. The code may include instructions executable by a processor to: send to a UE an indication of one or more encoding operations to be used by the UE to encode a compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both; receive from the UE an encoded, quantized, compressed data set after the compressed data set has been encoded following a quantization operation based on the one or more encoding operations; decode the encoded, quantized, compressed data set to generate a compressed data set based on the one or more encoding operations; and decode the compressed data set to generate a data set based on decoding the encoded, quantized, compressed data set by a neural network.

[0022] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, transmitting an indication of the one or more encoding operations may include acts, features, means, or instructions for transmitting one or more parameters corresponding to the one or more encoding operations, each of the one or more parameters corresponding to a respective encoding operation of the one or more encoding operations, and the quantized and compressed data set may be encoded based on the one or more parameters.

[0023] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, decoding the encoded, quantized, compressed data set may include operations, features, means, or instructions for decoding the encoded, quantized, compressed data set using a differential decoding operation prior to decoding the data set using a neural network.

[0024] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, decoding the encoded, quantized, compressed data set may include operations, features, means, or instructions for decoding the encoded, quantized, compressed data set using an entropy decoding operation prior to decoding the data set using a neural network.

[0025] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, receiving the encoded, quantized, compressed data set may include operations, features, means, or instructions for receiving the encoded, quantized, compressed data set that includes difference values ​​for data in the data set that may be based on initial values ​​of the data.

[0026] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, receiving the encoded, quantized, compressed data set may include operations, features, means, or instructions for receiving the encoded, quantized, compressed data set that includes difference values ​​for data in the data set that may be based on a previous reconstruction value of the data.

[0027] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, receiving the encoded, quantized, compressed data set may include operations, features, means, or instructions for receiving the encoded, quantized, compressed data set that includes difference values ​​for data in the data set that may be based on an initial reconstruction value of the data.

[0028] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the differential decoding operation may include encoding an amount of data of the compressed data set based on a previous value for that amount of data.

[0029] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the entropy decoding operation may include encoding the compressed data set using one or more symbols having lengths that vary based on the probability that the symbol occurs. [Brief description of the drawings]

[0030] [Figure 1] FIG. 1 illustrates an example of a wireless communication system that supports encoding techniques for neural network architectures according to aspects of the present disclosure. [Diagram 2] FIG. 1 illustrates an example of a wireless communication system that supports encoding techniques for neural network architectures according to aspects of the present disclosure. [Figure 3A] FIG. 1 illustrates an example of a compression procedure that supports an encoding technique for a neural network architecture, according to an aspect of the present disclosure. [Figure 3B] FIG. 1 illustrates an example of a compression procedure that supports an encoding technique for a neural network architecture, according to an aspect of the present disclosure. [Figure 4] FIG. 1 illustrates an example of a compression configuration that supports an encoding technique for a neural network architecture, according to aspects of the present disclosure. [Diagram 5] FIG. 1 illustrates an example of a compression and encoding configuration that supports an encoding technique for a neural network architecture, according to an aspect of the present disclosure. [Figure 6] FIG. 1 illustrates an example of a compression and encoding configuration that supports an encoding technique for a neural network architecture, according to an aspect of the present disclosure. [Figure 7] FIG. 1 illustrates an example of a process flow supporting an encoding technique for a neural network architecture, according to an aspect of the present disclosure. [Figure 8] FIG. 1 is a block diagram of a device that supports an encoding technique for a neural network architecture, according to an aspect of the disclosure. [Figure 9] FIG. 1 is a block diagram of a device that supports an encoding technique for a neural network architecture, according to an aspect of the disclosure. [Figure 10] FIG. 1 illustrates a block diagram of a communications manager that supports an encoding technique for a neural network architecture, according to an aspect of the disclosure. [Figure 11] FIG. 1 is a diagram of a system including devices that support encoding techniques for neural network architectures, according to aspects of the disclosure. [Figure 12] FIG. 1 is a block diagram of a device that supports an encoding technique for a neural network architecture, according to an aspect of the disclosure. [Figure 13] FIG. 1 is a block diagram of a device that supports an encoding technique for a neural network architecture, according to an aspect of the disclosure. [Figure 14]FIG. 1 illustrates a block diagram of a communications manager that supports an encoding technique for a neural network architecture, according to an aspect of the disclosure. [Figure 15] FIG. 1 is a diagram of a system including devices that support encoding techniques for neural network architectures, according to aspects of the disclosure. [Figure 16] 1 is a flowchart illustrating a method for supporting an encoding technique for a neural network architecture, according to an aspect of the present disclosure. [Figure 17] 1 is a flowchart illustrating a method for supporting an encoding technique for a neural network architecture, according to an aspect of the present disclosure. [Figure 18] 1 is a flowchart illustrating a method for supporting an encoding technique for a neural network architecture, according to an aspect of the present disclosure. [Figure 19] 1 is a flowchart illustrating a method for supporting an encoding technique for a neural network architecture, according to an aspect of the present disclosure. [Figure 20] 1 is a flowchart illustrating a method for supporting an encoding technique for a neural network architecture, according to an aspect of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0031] In some wireless communication systems, a user equipment (UE) may make several measurements of channel conditions as part of communicating with a base station. For example, the measurements may include per antenna port measurements of channel and interference (e.g., channel state feedback), power measurements from serving and neighboring cells, inter-Radio Access Technology (RAT) measurements (e.g., from Wireless Fidelity (WiFi) networks, etc.), sensor measurements, etc. These measurements may generate a large amount of data to be transmitted to the base station to assist the base station in network management. For example, a wireless communication system using an antenna panel with multiple elements may generate more measurement information than a wireless communication system using a single antenna or a smaller antenna panel with fewer elements. In some examples, the UE may compress the measurement results using a neural network to reduce the size of the transmission carrying the measurement results. In addition to compression techniques using neural networks, techniques for applying additional compression techniques of the measurement data are desired.

[0032] Techniques are described for compressing measurement data by a UE for transmission. The UE may measure one or more channel conditions. The UE may then compress the measurement data using a neural network. The output of the neural network may be quantized to provide data that is more likely to be communicated. In addition to neural network compression, the UE may use an additional layer of compression before sending a transmission to the base station. For example, the UE may use differential encoding, entropy encoding, or both to further compress the measurement data after compressing the data with the neural network and before sending a transmission to the base station. Differential encoding may be an example of encoding the difference between two measurement results rather than encoding the absolute value of the measurement results. For example, differential encoding may use a previous value, an initial value, a reconstructed value, an initial reconstructed value, or a combination thereof to indicate the difference value. In some examples, the UE may perform differential encoding, entropy encoding, or both to further compress the data after the quantization step associated with neural network processing. Additionally or alternatively, differential encoding may be performed at the input stage of the compression operation, where bits representing the difference between the measurement results are first encoded and then input to the neural network for processing. The base station may then use differential decoding, entropy decoding, or both when decoding the compressed encoded transmission from the UE. In some examples, the base station may transmit an indication of the differential and entropy encoding (e.g., and parameters for each encoding) that the UE should use. Thus, the encoding operations performed by the transmitting device (e.g., UE) and the decoding operations performed by the receiving device (e.g., base station) may be coordinated.

[0033] Aspects of the present disclosure are first described in the context of a wireless communication system. Additionally, aspects of the present disclosure are illustrated through additional wireless communication systems, compression procedures, compression configurations, compression and encoding configurations, and process flows. Aspects of the present disclosure are further illustrated by and described with reference to apparatus diagrams, system diagrams, and flow charts relating to encoding techniques for neural network architectures.

[0034] FIG. 1 illustrates an example of a wireless communication system 100 supporting encoding techniques for neural network architectures according to aspects of the disclosure. The wireless communication system 100 may include one or more base stations 105, one or more UEs 115, and a core network 130. In some examples, the wireless communication system 100 may be a Long Term Evolution (LTE) network, an LTE-Advanced (LTE-A) network, an LTE-A Pro network, or a New Radio (NR) network. In some examples, the wireless communication system 100 may support enhanced broadband communications, ultra-reliable (e.g., mission-critical) communications, low latency communications, communications with low-cost and low-complexity devices, or any combination thereof.

[0035] The base stations 105 may be distributed throughout a geographic area to form the wireless communication system 100 and may be devices of different forms or with different capabilities. The base stations 105 and the UEs 115 may communicate wirelessly via one or more communication links 125. Each base station 105 may provide a coverage area 110 over which the UEs 115 and the base station 105 may establish one or more communication links 125. The coverage area 110 may be an example of a geographic area over which the base stations 105 and the UEs 115 may support communication of signals according to one or more radio access technologies.

[0036] The UEs 115 may be distributed throughout the coverage area 110 of the wireless communication system 100, and each UE 115 may be fixed or mobile or both at different times. The UEs 115 may be devices of different forms or with different capabilities. Some example UEs 115 are shown in FIG. 1. The UEs 115 described herein may be capable of communicating with various types of devices, such as other UEs 115, base stations 105, or network equipment (e.g., core network nodes, relay devices, integrated access and backhaul (IAB) nodes, or other network equipment) as shown in FIG. 1.

[0037] The base stations 105 may communicate with the core network 130, with each other, or both. For example, the base stations 105 may interface with the core network 130 through one or more backhaul links 120 (e.g., via an S1, N2, N3, or other interface). The base stations 105 may communicate with each other via the backhaul links 120 (e.g., via an X2, Xn, or other interface), either directly (e.g., directly between the base stations 105), or indirectly (e.g., via the core network 130), or both. In some examples, the backhaul links 120 may be or include one or more wireless links.

[0038] One or more of the base stations 105 described herein may include or be referred to as a base transceiver station, wireless base station, access point, wireless transceiver, NodeB, eNodeB (eNB), next generation NodeB or giga-NodeB (any of which may be referred to as a gNB), Home NodeB, Home eNodeB, or other suitable terminology by one skilled in the art.

[0039] The UE 115 may include or be referred to as a mobile device, a wireless device, a remote device, a handheld device, or a subscriber device, or some other suitable terminology, and a "device" may be referred to as a unit, a station, a terminal, or a client, among other things. The UE 115 may also include or be referred to as a personal electronic device, such as a mobile phone, a personal digital assistant (PDA), a tablet computer, a laptop computer, or a personal computer. In some examples, the UE 115 may include or be referred to as a wireless local loop (WLL) station, an Internet of Things (IoT) device, an Internet of Everything (IoE) device, or a machine type communication (MTC) device, among other things, which may be implemented in various articles, such as an appliance, or a vehicle, a meter, among other things.

[0040] The UEs 115 described herein may be capable of communicating with various types of devices, such as other UEs 115 that may act as relays, as shown in FIG. 1, as well as base stations 105 and network equipment, including macro eNBs or gNBs, small cell eNBs or gNBs, or relay base stations, among others.

[0041] The UE 115 and the base station 105 may wirelessly communicate with each other via one or more communication links 125 on one or more carriers. The term “carrier” may refer to a set of radio frequency spectrum resources having a defined physical layer structure to support the communication link 125. For example, a carrier used for the communication link 125 may include a portion (e.g., a bandwidth portion (BWP)) of a radio frequency spectrum band that operates according to one or more physical layer channels for a given radio access technology (e.g., LTE, LTE-A, LTE-A Pro, NR). Each physical layer channel may carry collection signaling (e.g., synchronization signals, system information), control signaling that coordinates operation on the carrier, user data, or other signaling. The wireless communication system 100 may support communication with the UE 115 using carrier aggregation or multi-carrier operation. The UE 115 may be configured with multiple downlink component carriers and one or more uplink component carriers according to a carrier aggregation configuration. Carrier aggregation may be used with both frequency division duplex (FDD) and time division duplex (TDD) component carriers.

[0042] In some examples (e.g., in a carrier aggregation configuration), a carrier may also have collection or control signaling to coordinate operation with respect to other carriers. A carrier may be associated with a frequency channel (e.g., evolved universal mobile telecommunication system terrestrial radio access (E-UTRA) absolute radio frequency channel number (EARFCN)) and may be arranged according to a channel raster for discovery by the UE 115. A carrier may operate in a standalone mode, where initial collection and connection may be made by the UE 115 over the carrier, or the carrier may operate in a non-standalone mode, where connection is anchored using a different carrier (e.g., of the same or different radio access technology).

[0043] The communication links 125 shown in the wireless communication system 100 may include uplink transmissions from the UE 115 to the base station 105 or downlink transmissions from the base station 105 to the UE 115. A carrier may carry downlink or uplink communications (e.g., in FDD mode) or may be configured to carry downlink and uplink communications (e.g., in TDD mode).

[0044] A carrier may be associated with a particular bandwidth of the radio frequency spectrum, and in some examples, the carrier bandwidth may be referred to as the carrier or the “system bandwidth” of the wireless communication system 100. For example, the carrier bandwidth may be one of a number of determined bandwidths for a particular radio access technology carrier (e.g., 1.4, 3, 5, 10, 15, 20, 40, or 80 megahertz (MHz)). The devices of the wireless communication system 100 (e.g., the base station 105, the UE 115, or both) may have a hardware configuration that supports communication on a particular carrier bandwidth or may be configurable to support communication on one of a set of carrier bandwidths. In some examples, the wireless communication system 100 may include a base station 105 or UE 115 that supports simultaneous communication via a carrier associated with multiple carrier bandwidths. In some examples, each served UE 115 may be configured to operate on a portion (e.g., a sub-band, BWP) or all of the carrier bandwidth.

[0045] A signal waveform transmitted on a carrier may be composed of multiple subcarriers (e.g., using a multicarrier modulation (MCM) technique such as orthogonal frequency division multiplexing (OFDM) or discrete Fourier transform spread OFDM (DFT-S-OFDM)). In a system employing MCM techniques, a resource element may consist of one symbol period (e.g., the time length of one modulation symbol) and one subcarrier, where the symbol period and the subcarrier spacing are inversely proportional. The amount of bits carried by each resource element may depend on the modulation scheme (e.g., the order of the modulation scheme, the coding rate of the modulation scheme, or both). Thus, the more resource elements the UE 115 receives and the higher the order of the modulation scheme, the higher the data rate may be for the UE 115. Wireless communication resources may refer to a combination of radio frequency spectrum resources, time resources, and spatial resources (e.g., spatial layers or beams), and the use of multiple spatial layers may further increase the data rate or data integrity for communication with the UE 115.

[0046] One or more numerologies for a carrier may be supported, where the numerology may include a subcarrier spacing (Δf) and a cyclic prefix. A carrier may be divided into one or more BWPs having the same or different numerologies. In some examples, a UE 115 may be configured with multiple BWPs. In some examples, a single BWP for a carrier may be active at a given time, and communication for the UE 115 may be limited to one or more active BWPs.

[0047] The time interval for the base station 105 or the UE 115 may be, for example, T s =1 / (Δf max N f ) seconds, where Δf max may represent the maximum supported subcarrier spacing, and N fmay represent the maximum supported discrete Fourier transform (DFT) size. The communication resource time intervals may be organized according to radio frames, each having a specified time length (e.g., 10 milliseconds (ms)). Each radio frame may be identified by a system frame number (SFN) (e.g., ranging from 0 to 1023).

[0048] Each frame may include multiple consecutively numbered subframes or slots, and each subframe or slot may have the same time length. In some examples, a frame may be divided (e.g., in the time domain) into subframes, and each subframe may be further divided into a certain amount of slots. Alternatively, each frame may include a variable amount of slots, and the amount of slots may depend on the subcarrier spacing. Each slot may include a certain amount of symbol periods (e.g., depending on the length of a cyclic prefix prepended to each symbol period). In some wireless communications systems 100, a slot may be further divided into multiple minislots containing one or more symbols. Excluding the cyclic prefix, each symbol period may include one or more (e.g., N f The time length of a symbol period may depend on the subcarrier spacing or the frequency band of operation.

[0049] A subframe, slot, minislot, or symbol may be the smallest scheduling unit (e.g., in the time domain) of the wireless communications system 100 and may be referred to as a transmission time interval (TTI). In some examples, the TTI length (e.g., the amount of symbol periods in a TTI) may be variable. Additionally or alternatively, the smallest scheduling unit of the wireless communications system 100 may be dynamically selected (e.g., within a burst of shortened TTIs (sTTIs)).

[0050] The physical channels may be multiplexed on the carriers according to various techniques. The physical control channels and the physical data channels may be multiplexed on the downlink carriers using, for example, one or more of a time division multiplexing (TDM), a frequency division multiplexing (FDM), or a hybrid TDM-FDM technique. A control region (e.g., a control resource set (core set)) for the physical control channels may be defined by an amount of symbol periods and may extend across the system bandwidth of the carrier or a subset of the system bandwidth. One or more control regions (e.g., core sets) may be configured for a set of UEs 115. For example, one or more of the UEs 115 may monitor or search the control region for control information according to one or more search space sets, and each search space set may include one or more control channel candidates at one or more aggregation levels arranged in a cascaded manner. The aggregation level for control channel candidates may refer to the amount of control channel resources (e.g., control channel elements (CCEs)) associated with coded information for a control information format having a given payload size. The search space sets may include a common search space set configured for transmitting control information to multiple UEs 115 and a UE-specific search space set for transmitting control information to a specific UE 115.

[0051] Each base station 105 may provide communication coverage via one or more cells, e.g., macro cells, small cells, hot spots, or other types of cells, or any combination thereof. The term “cell” may refer to a logical communication entity used for communication with the base station 105 (e.g., on a carrier) and may be associated with an identifier (e.g., a physical cell identifier (PCID), a virtual cell identifier (VCID), or other) to distinguish neighboring cells. In some examples, a cell may also refer to a geographic coverage area 110 or a portion (e.g., a sector) of the geographic coverage area 110 in which the logical communication entity operates. Such a cell may range from a smaller area (e.g., a structure, a subset of a structure) to a larger area depending on various factors such as the capabilities of the base station 105. For example, a cell may be or include, among others, a building, a subset of a building, or an outside space between or overlapping with the geographic coverage area 110.

[0052] A macro cell generally covers a relatively large geographic area (e.g., a radius of several kilometers) and may allow unrestricted access by UEs 115 subscribing to the service of a network provider supporting the macro cell. A small cell may be associated with a lower power base station 105 compared to a macro cell, and the small cell may operate in the same or different (e.g., licensed, unlicensed) frequency band as the macro cell. A small cell may provide unrestricted access to UEs 115 subscribing to the service of a network provider, or may provide restricted access to UEs 115 that have an association with the small cell (e.g., UEs 115 in a closed subscriber group (CSG), UEs 115 associated with a user in a home or office). A base station 105 may support one or more cells and may support communication on one or more cells using one or more component carriers.

[0053] In some examples, a carrier may support multiple cells, and different cells may be configured according to different protocol types (e.g., MTC, Narrowband IoT (NB-IoT), enhanced Mobile Broadband (eMBB)) that may provide access to different types of devices.

[0054] In some examples, the base stations 105 may be mobile and therefore provide communication coverage to moving geographic coverage areas 110. In some examples, the different geographic coverage areas 110 associated with different technologies may overlap, but the different geographic coverage areas 110 may be supported by the same base station 105. In other examples, overlapping geographic coverage areas 110 associated with different technologies may be supported by different base stations 105. The wireless communication system 100 may include a heterogeneous network, for example, where different types of base stations 105 provide coverage to various geographic coverage areas 110 using the same or different radio access technologies.

[0055] The wireless communications system 100 may support synchronous or asynchronous operation. For synchronous operation, the base stations 105 may have similar frame timing and transmissions from different base stations 105 may be approximately aligned in time. For asynchronous operation, the base stations 105 may have different frame timing and transmissions from different base stations 105 may not be aligned in time, in some examples. The techniques described herein may be used for either synchronous or asynchronous operation.

[0056] Some UEs 115, such as MTC or IoT devices, may be low-cost or low-complexity devices and may provide automated communication between machines (e.g., via machine-to-machine (M2M) communication). M2M communication or MTC may refer to data communication technologies that allow devices to communicate with each other or with the base station 105 without human intervention. In some examples, M2M communication or MTC may include communication from devices that incorporate sensors or meters to measure or capture information and relay that information to a central server or application program that utilizes such information or presents the information to a human who interacts with the application program. Some UEs 115 may be designed to collect information or enable automated behavior of machines or other devices. Examples of applications for MTC devices include smart metering, inventory monitoring, water level monitoring, equipment monitoring, healthcare monitoring, wildlife monitoring, weather and geological event monitoring, fleet management and tracking, remote security sensing, physical access control, and transaction-based business billing.

[0057] Some UEs 115 may be configured to use operating modes that reduce power consumption, such as half-duplex communication (e.g., a mode that supports one-way communication via transmission or reception, but not simultaneous transmission and reception). In some examples, the half-duplex communication may be performed at a reduced peak rate. Other power conservation techniques for the UE 115 include entering a power-saving deep sleep mode when not engaged in active communication, operating over a limited bandwidth (e.g., in accordance with narrowband communication), or a combination of these techniques. For example, some UEs 115 may be configured for operation using a narrowband protocol type associated with a defined portion or range (e.g., a set of subcarriers or resource blocks (RBs)) within a carrier, within a guard band of the carrier, or outside of a carrier.

[0058] The wireless communication system 100 may be configured to support ultra-reliable or low latency communications, or various combinations thereof. For example, the wireless communication system 100 may be configured to support ultra-reliable low latency communications (URLLC) or mission-critical communications. The UE 115 may be designed to support ultra-reliable, low latency, or critical functions (e.g., mission-critical functionality). Ultra-reliable communications may include private or group communications and may be supported by one or more mission-critical services, such as mission-critical push-to-talk (MCPTT), mission-critical video (MCVideo), or mission-critical data (MCData). Support for mission-critical functions may include service prioritization, and the mission-critical services may be used for public safety or general commercial applications. The terms ultra-reliable, low latency, mission-critical, and ultra-reliable low latency may be used interchangeably herein.

[0059] In some examples, the UE 115 may also be able to communicate directly with other UEs 115 via device-to-device (D2D) communication links 135 (e.g., using a peer-to-peer (P2P) protocol or a D2D protocol). One or more UEs 115 utilizing D2D communication may be within the geographic coverage area 110 of the base station 105. Other UEs 115 in such a group may be outside the geographic coverage area 110 of the base station 105 or may not be able to receive transmissions from the base station 105 in some examples. In some examples, a group of UEs 115 communicating via D2D communication may utilize a one-to-many (1:M) system such that each UE 115 transmits to every other UE 115 in the group. In some examples, the base station 105 facilitates scheduling of resources for D2D communication. In other cases, D2D communication is performed between UEs 115 without the involvement of the base station 105.

[0060] In some systems, the D2D communication link 135 may be an example of a communication channel between vehicles (e.g., UE 115), such as a sidelink communication channel. In some examples, the vehicles may communicate using vehicle-to-everything (V2X) communication, vehicle-to-vehicle (V2V) communication, or some combination thereof. The vehicles may signal information related to traffic conditions, signal scheduling, weather, safety, emergency situations, or any other information related to the V2X system. In some examples, the vehicles in the V2X system may communicate with roadside infrastructure, such as roadside units, or with a network via one or more network nodes (e.g., base stations 105) using vehicle-to-network (V2N) communication, or both.

[0061] The core network 130 may provide user authentication, access authorization, tracking, Internet Protocol (IP) connectivity, and other access, routing, or mobility functions. The core network 130 may be an evolved packet core (EPC) or 5G core (5GC), which may include at least one control plane entity (e.g., a mobility management entity (MME), an access and mobility management function (AMF)) that manages access and mobility, and at least one user plane entity (e.g., a serving gateway (S-GW), a packet data network (PDN) gateway (P-GW), or a user plane function (UPF)) that routes packets or interconnects to external networks. The control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management for UEs 115 served by base stations 105 associated with the core network 130. User IP packets may be forwarded through a user plane entity, which may provide IP address allocation as well as other functions. The user plane entity may be connected to one or more network operators' IP services 150. The IP services 150 may include access to the Internet, an intranet, an IP Multimedia Subsystem (IMS), or packet-switched streaming services.

[0062] Some of the network devices, such as the base station 105, may include subcomponents, such as an access network entity 140, which may be an example of an access node controller (ANC). Each access network entity 140 may communicate with the UE 115 through one or more other access network transmitting entities 145, which may be referred to as a radio head, a smart radio head, or a transmit / receive point (TRP). Each access network transmitting entity 145 may include one or more antenna panels. In some configurations, various functions of each access network entity 140 or base station 105 may be distributed across various network devices (e.g., radio heads and ANCs) or integrated into a single network device (e.g., the base station 105).

[0063] The wireless communication system 100 may operate using one or more frequency bands, typically in the range of 300 megahertz (MHz) to 300 gigahertz (GHz). The 300 MHz to 3 GHz region is commonly referred to as the ultra-high frequency (UHF) region or decimeter band because the wavelengths range from approximately 1 decimeter to 1 meter in length. Although UHF waves may be blocked or redirected by buildings and environmental features, the waves may penetrate structures sufficiently for a macrocell to serve UEs 115 located indoors. Transmission of UHF waves may be associated with smaller antennas and shorter distances (e.g., less than 100 kilometers) compared to transmissions using lower frequencies and longer waves in the short wave (HF) or very high frequency (VHF) portions of the spectrum below 300 MHz.

[0064] The wireless communication system 100 may also operate in the super high frequency (SHF) region, using a frequency band from 3 GHz to 30 GHz, also referred to as the centimeter band, or in the extremely high frequency (EHF) region of the spectrum, also referred to as the millimeter band (e.g., from 30 GHz to 300 GHz). In some examples, the wireless communication system 100 may support millimeter wave (mmW) communications between the UE 115 and the base station 105, and the EHF antennas of the respective devices may be smaller and more closely spaced than the UHF antennas. In some examples, this may facilitate the use of antenna arrays within the devices. However, propagation of EHF transmissions may experience more atmospheric attenuation and shorter distances than SHF or UHF transmissions. The techniques disclosed herein may be employed across transmissions using one or more different frequency regions, and the designated use of the bands across these frequency regions may vary by country or regulatory body.

[0065] The wireless communication system 100 may utilize both licensed and unlicensed radio frequency spectrum bands. For example, the wireless communication system 100 may employ License Assisted Access (LAA), LTE-Unlicensed (LTE-U) radio access technology, or NR technology in an unlicensed band, such as the 5 GHz Industrial, Scientific, and Medical (ISM) band. When operating in an unlicensed radio frequency spectrum band, devices such as the base station 105 and the UE 115 may employ carrier sensing for contention detection and avoidance. In some examples, operation in an unlicensed spectrum may be based on a carrier aggregation configuration in conjunction with component carriers operating in a licensed band (e.g., LAA). Operation in an unlicensed spectrum may include downlink transmissions, uplink transmissions, P2P transmissions, or D2D transmissions, among others.

[0066] The base station 105 or UE 115 may be equipped with multiple antennas that may be used to employ techniques such as transmit diversity, receive diversity, multiple-input multiple-output (MIMO) communications, or beamforming. The antennas of the base station 105 or UE 115 may be located in one or more antenna arrays or antenna panels that may support MIMO operations or transmit or receive beamforming. For example, one or more base station antennas or antenna arrays may be collocated in an antenna assembly such as an antenna tower. In some examples, the antennas or antenna arrays associated with the base station 105 may be located in various geographic locations. The base station 105 may have an antenna array with a certain number of rows and columns of antenna ports that the base station 105 may use to support beamforming of communications with the UE 115. Similarly, the UE 115 may have one or more antenna arrays that may support various MIMO or beamforming operations. Additionally or alternatively, the antenna panels may support radio frequency beamforming for signals transmitted through the antenna ports.

[0067] A base station 105 or a UE 115 may use MIMO communications to exploit multipath signal propagation and increase spectral efficiency by transmitting or receiving multiple signals via different spatial layers. Such techniques may be referred to as spatial multiplexing. The multiple signals may be transmitted by a transmitting device via different antennas or different combinations of antennas, for example. Similarly, the multiple signals may be received by a receiving device via different antennas or different combinations of antennas. Each of the multiple signals may be referred to as a separate spatial stream and may carry bits related to the same data stream (e.g., the same codeword) or different data streams (e.g., different codewords). The different spatial layers may be associated with different antenna ports used for channel measurements and reporting. MIMO techniques include single-user MIMO (SU-MIMO), in which multiple spatial layers are transmitted to the same receiving device, and multi-user MIMO (MU-MIMO), in which multiple spatial layers are transmitted to multiple devices.

[0068] Beamforming, sometimes referred to as spatial filtering, directional transmission, or directional reception, is a signal processing technique that may be used in a transmitting or receiving device (e.g., base station 105, UE 115) to shape or steer an antenna beam (e.g., transmit beam, receive beam) along a spatial path between the transmitting device and the receiving device. Beamforming may be achieved by combining signals communicated through antenna elements of an antenna array such that some signals propagating in a particular orientation relative to the antenna array are subject to constructive interference, while other signals are subject to destructive interference. Adjustment of signals communicated through antenna elements may include a transmitting or receiving device applying an amplitude offset, a phase offset, or both, to signals carried through an antenna element associated with the device. The adjustments associated with each of the antenna elements may be defined by a beamforming weight set associated with a particular orientation (e.g., relative to the antenna array of the transmitting or receiving device, or to some other orientation).

[0069] The base station 105 or the UE 115 may use beam sweeping techniques as part of a beamforming operation. For example, the base station 105 may use multiple antennas or antenna arrays (e.g., antenna panels) to perform a beamforming operation for directional communication with the UE 115. Some signals (e.g., synchronization signals, reference signals, beam selection signals, or other control signals) may be transmitted multiple times by the base station 105 in different directions. For example, the base station 105 may transmit signals according to different beamforming weight sets associated with different directions of transmission. The transmissions in different beam directions may be used (e.g., by a transmitting device such as the base station 105 or by a receiving device such as the UE 115) to identify beam directions for later transmissions or receptions by the base station 105.

[0070] The wireless communication system 100 may be a packet-based network that operates according to a layered protocol stack. In the user plane, communication at the bearer or Packet Data Convergence Protocol (PDCP) layer may be IP-based. The Radio Link Control (RLC) layer may perform packet segmentation and reassembly to communicate on logical channels. The Medium Access Control (MAC) layer may perform priority handling and multiplexing of logical channels into transport channels. The MAC layer may also use error detection techniques, error correction techniques, or both to support retransmissions at the MAC layer to improve link efficiency. In the control plane, the Radio Resource Control (RRC) protocol layer may establish, configure, and maintain an RRC connection between the UE 115 and the base station 105 or core network 130, which supports radio bearers for user plane data. In the physical layer, the transport channels may be mapped to physical channels.

[0071] The UE 115 and the base station 105 may support retransmission of data to increase the likelihood of successful reception of the data. Hybrid Automatic Repeat Request (HARQ) feedback is one technique for increasing the likelihood that data is correctly received on the communication link 125. HARQ may include a combination of error detection (e.g., using a Cyclic Redundancy Check (CRC)), forward error correction (FEC), and retransmission (e.g., Automatic Repeat Request (ARQ)). HARQ may improve throughput at the MAC layer in poor radio conditions (e.g., low signal-to-noise conditions). In some examples, a device may support same-slot HARQ feedback, in which the device may provide HARQ feedback in a particular slot for data received in a previous symbol in that slot. In other cases, the device may provide HARQ feedback in a subsequent slot or according to some other time interval.

[0072] Machine learning, particularly deep machine learning, has become a popular tool in wireless communication systems to facilitate more efficient communication. For example, among other benefits, a machine learning model deployed in the UE 115 may enable the UE 115 to make decisions or perform actions (e.g., using prediction or regression or other goals) without additional signaling from the base station 105 (e.g., the UE 115 may make inferences about actions to take based on input or detected events). In addition, the machine learning model may enable the UE 115 to prepare transmissions for more efficient communication (e.g., using classification or compression or other goals). Before the machine learning model can be deployed to the device, the machine learning model may be prepared and trained (e.g., using a dataset).

[0073] A machine learning model using a neural network may be deployed to a device (e.g., UE 115) for different applications (e.g., prediction, classification, compression, regression, or other goals). For example, the machine learning model may include one or more parameters (e.g., prepared datasets) that, when identified by the device, enable or support the corresponding application in the device. To build and further train the machine learning model, the network device may collect different datasets to identify the impact or effect of the datasets on the different applications. That is, the machine learning model may be trained on one or more datasets using a neural network, and when real-world data is input into the machine learning model, the machine learning model may generate an output based on the datasets.

[0074] In addition, the UE 115 may make several measurements of channel conditions as part of communicating with the base station 105. For example, the measurements may include per antenna port measurements of channel and interference (e.g., channel state feedback), power measurements from serving and neighboring cells, inter-RAT measurements (e.g., from WiFi networks, etc.), sensor measurements, etc. These measurements may generate a large amount of data to be transmitted to the base station 105 to assist the base station 105 in network management. In some cases, the UE 115 may utilize machine learning models or neural networks to compress this large amount of data to be transmitted.

[0075] In some examples, quantities measured by the UE 115 (e.g., in a 5G network) may depend on multiple parameters. For example, multiple parameters that may affect measurements may include measurements of antenna design and placement at the UE 115 and their time-varying occlusion, environmental parameters (e.g., location, shadowing, presence and movement of reflectors in the vicinity of the UE 115 and / or base station 105, where placement of reflectors may also produce tap-to-tap correlations, such as resolution of a wide path / beam splitting into multiple multiple paths), loading on the cell (e.g., resulting in handoffs), movement of the subject UE 115 (e.g., changes in its orientation), etc. To account for these types of changing parameters that may affect measurements, the UE 115 may use or be implemented by a neural network that learns the dependence of the measured quantities on individual parameters, separates those measured quantities through various layers, and compresses the measurements while reducing (e.g., minimizing) compression loss. For example, the UE 115 may use a neural network to compress the measurements to reduce the size of the transmission carrying the measurements. However, further techniques are desired to improve measurement data compression techniques using neural networks.

[0076] The wireless communication system 100 may support adding additional layers to the compression operation when the UE 115 is compressing data in a transmission before sending the transmission to the base station 105. For example, the UE 115 may measure one or more channel conditions and then use a neural network to compress the measurement data. In some examples, the UE 115 may quantize the output of the neural network to provide data that is more likely to be communicated. Subsequently, after the neural network compression, the UE 115 may add further layers to further compress the data, and the UE 115 may use differential encoding, entropy encoding, or both to further compress and encode the measurement data before sending the transmission to the base station. Differential encoding may be an example of encoding the difference between two measurement results rather than encoding the absolute value of the measurement results. For example, differential encoding may use a previous value, an initial value, a reconstructed value, an initial reconstructed value, or a combination thereof to indicate the difference value. The base station 105 may then use differential decoding, entropy decoding, or both when decoding the encoded, quantized, compressed transmission from the UE 115. In some examples, the base station 105 may transmit an indication of the differential encoding and entropy encoding (eg, and parameters for each encoding) that the UE 115 should use.

[0077] 2 illustrates an example of a wireless communication system 200 supporting encoding techniques for neural network architectures according to aspects of the disclosure. In some examples, the wireless communication system 200 may implement or be implemented by aspects of the wireless communication system 100. For example, the wireless communication system 200 may include a base station 105-a and a UE 115-a, which may be examples of corresponding base stations 105 and UEs 115, respectively, as described with reference to FIG. 1. In addition, the base station 105-a and the UE 115-a may communicate on resources of a carrier 205 (e.g., for downlink communications) and resources of a carrier 210 (e.g., for uplink communications). Although shown as separate carriers, the carrier 205 and the carrier 210 may include the same or different resources (e.g., time and frequency resources) for corresponding transmissions.

[0078] As described herein, using the nature of the quantity to be compressed (e.g., data in a dataset), the UE 115-a may use a neural network to extract and compress each feature (e.g., dimension) that affects the quantity step by step. For example, the UE 115-a may identify a feature (e.g., dimension) to compress. In some examples, the UE 115-a may perform a type of operation in that dimension and a general operation in the other dimension. For example, the UE 115-a may use a fully connected layer in the first dimension and a convolution (e.g., point-wise convolution) in the other dimension. The UE 115-a may then perform extraction that includes additional stacked layers. For example, the additional stacked layers may include convolutional layers, fully connected layers, or other layers with or without activations (e.g., residual neural network (ResNet) layers). After extraction, the neural network utilized in the UE 115-a may compress the feature. For example, the neural network may use a convolutional layer or a fully connected layer or another type of layer for this compression. The UE 115-a may repeat this process for subsequent features. After each feature is extracted and compressed, the UE 115-a may use one or more additional compression layers (e.g., a convolutional layer, a fully connected layer, or another type of layer). Using techniques described herein, the UE 115-a may then perform additional encoding for the final compression, such as differential encoding, entropy encoding, or both.

[0079] Differential encoding may include encoding the difference between two measurements rather than encoding the absolute value of the measurements. For example, a first signal power measurement obtained at a first time may be compared to a second signal power measurement obtained at a second time. In differential encoding, the difference between the first and second signal power measurements may be communicated rather than the absolute value of the second signal power measurement. Some differential data may use fewer bits than the absolute value of the data because some measurements do not change much over time. Additionally, entropy encoding may include compressing the amount of coded bits to reduce the amount of bits in the transmission. In some examples, entropy coding schemes may use symbols with an amount of bits inversely proportional to the probability that the symbol appears. For example, symbols that are more likely to appear may be coded using fewer bits than symbols that are less likely to appear.

[0080] In some examples, the UE 115-a may perform differential encoding, entropy encoding, or both to further compress the data after the quantization step associated with the neural network processing. Additionally or alternatively, differential encoding may be performed at the input stage of the compression operation, where bits representing differences between measurements are first encoded and then input to the neural network for processing. The base station 105-a may then use differential decoding, entropy decoding, or both when decoding the compressed and encoded transmission from the UE 115-a.

[0081] Prior to performing these compression and encoding operations, the base station 105-a may indicate that the UE 115-a should perform different compression and encoding operations. For example, the base station 105-a may transmit an indication of encoding parameters 215 to the UE 115-a (e.g., over the carrier 205). In some examples, the encoding parameters 215 may include differential encoder parameters 220, entropy encoder parameters 225, or both. The one or more encoder parameters may enable or indicate to the UE 115-a to use a corresponding encoder when compressing and encoding data (e.g., measurement data) before transmitting the data to the base station 105-a. For example, the UE 115-a may detect or determine the data set 230 to be compressed and encoded based on the encoding parameters 215 (e.g., including differential encoder parameters 220, entropy encoder parameters 225, or both). The UE 115-a may then transmit the compressed encoded data set 235 to the base station 105-a (e.g., over the carrier 210) based on having performed a differential encoder operation (e.g., according to the differential encoder parameters 220), an entropy encoder operation (e.g., according to the entropy encoder parameters 225), or both. The base station 105-a may then decode the compressed encoded data set 235 based on the differential decoder operation, the entropy decoder operation, or both.

[0082] In some examples, the encoding parameters 215 may indicate how the UE 115-a should perform the corresponding encoder operation. For example, according to the differential encoder parameters 220, the base station 105-a may indicate which previous values ​​the UE 115-a should use to perform the differential encoder operation. In some implementations, the UE 115-a may use an initial value of some data (e.g., in an intra-coded frame (I frame)) to determine a differential value for that data at a later time instance (e.g., in a predicted frame (P frame)). Additionally or alternatively, the UE 115-a may use an earlier reconstructed value of some data to determine a differential value for that data at a later time instance. In some examples, the UE 115-a may use an initial reconstructed value of some data to determine a differential value for that data at a later time instance. Additionally or alternatively, the base station 105-a may indicate how the UE 115-a should perform the entropy encoding operation via the entropy encoder parameters 225. For example, the entropy encoder parameters 225 may indicate the type of entropy encoder operation to be performed (e.g., Huffman encoding, arithmetic encoding, Embedded Zerotree Wavelet (EZW) encoding, Lempel-Ziv (LZ) entropy coding, etc.) as well as additional parameters to enable the entropy encoder operation.

[0083] As described herein, the UE 115-a may perform a differential encoder operation, an entropy encoder operation, or both, on the output of the single-shot encoder. For example, the UE 115-a may first encode the data set 230 using a single-shot encoder (e.g., an additional encoder other than the differential encoder and the entropy encoder) to compress and encode the data set 230. In some examples, after the data set 230 is encoded using the single-shot encoder, the UE 115-a may quantize the encoded data set (e.g., the encoded and compressed data set). Quantizing the encoded data set may include storing or converting values ​​in the encoded data set to a lower bit width than a floating-point prediction (e.g., floating-point values ​​are converted to bits so that values ​​in the encoded data set are represented by integers rather than floating-point values). Once the encoded data set is quantized (e.g., the data set is now encoded, quantized, and compressed), the UE 115-a may then perform a differential encoder operation, an entropy encoder operation, or both, before further transmitting the encoded, quantized, and compressed data set to the base station 105-a. Additionally or alternatively, the UE 115-a may perform a differential encoder operation at the input stage to a single-shot encoder and perform the remaining operations described herein.

[0084] In some examples, the UE 115-a may determine when to perform a differential encoder operation, an entropy encoder operation, or both in association with a single-shot encoder (e.g., at an input or output stage) based on a corresponding indicated parameter for each encoder operation. For example, the differential encoder parameters 220 may indicate when the UE 115-a should perform a differential encoder operation (e.g., at an input or output stage of a single-shot encoder operation), and the entropy encoder parameters 225 may indicate when the UE 115-a should perform an entropy encoder operation (e.g., at an output stage of a single-shot encoder operation). Additionally or alternatively, the UE 115-a may be pre-configured as to when these encoder operations should be performed.

[0085] 2, the UE 115-a is shown as performing different compression and encoding operations, any encoding device (e.g., a base station 105, a TRP, another type of UE 115, etc.) may perform the techniques described herein to compress and encode a data set before transmitting the data set to an additional device. In addition, the base station 105-a is shown as receiving and decoding a compressed and encoded data set 235 (e.g., an encoded, quantized, compressed data set), however, any decoding device (e.g., a UE 115, a TRP, another type of base station 105, etc.) may perform the techniques described herein to decode the compressed and encoded data set 235.

[0086] 3A and 3B show examples of a compression procedure 300 and a compression procedure 301, respectively, that support encoding techniques for neural network architectures according to aspects of the disclosure. In some examples, the compression procedure 300 and the compression procedure 301 may implement or be implemented by aspects of the wireless communication system 100, the wireless communication system 200, or both. For example, an encoding device (e.g., the UE 115 or an additional encoding device) may be configured to perform one or more operations on samples (e.g., data) received via one or more antennas of the encoding device to compress the samples. A decoding device (e.g., the base station 105 or an additional decoding device) may then be configured to decode the compressed samples to determine information such as channel condition feedback.

[0087] In some examples, the encoding device may identify features to compress. For example, the encoding device may perform a first type of operation in a first dimension associated with the features to compress. The encoding device may perform a second type of operation in other dimensions (e.g., in all other dimensions). For example, the encoding device may perform a full connect operation in the first dimension and a convolution (e.g., a point-wise convolution) in the other dimensions. The identified features to compress may be input 305 (e.g., h(t) or h(t)) for the compression procedure 300. in )) The difference operations shown for the compression procedure 300 may include multiple neural network layers and / or operations. The neural networks of the encoding and decoding devices may be formed by one or more concatenations of the operations shown.

[0088] The encoding device may perform spatial feature extraction 310 on the data (e.g., input 305). Subsequently, the encoding device may perform tap region feature extraction 315 on the data. In some examples, the encoding device may perform tap region feature extraction before performing spatial feature extraction. In addition, the extraction operation may include multiple operations. For example, the multiple operations may include one or more convolution operations, one or more full connect operations, etc., which may be activated or deactivated. In some examples, the extraction operation may include one or more ResNet operations.

[0089] After performing spatial feature extraction 310 and tap region feature extraction 315 (e.g., an extraction operation), the encoding device may compress the extracted one or more features using feature compression 320. In some examples, feature compression 320 (e.g., a compression operation) may include one or more operations, such as one or more convolution operations, one or more full connect operations, etc. After compression, the number of bits of the output may be less than the number of bits of the input.

[0090] The encoding device may then perform quantization 325 (e.g., a quantization operation). In some examples, the encoding device may perform quantization 325 after flattening the output of the compression operation and / or after flattening the output and then performing a full-connection operation. Using spatial feature extraction 310, tap region feature extraction 315, and feature compression 320 may represent performing or using a single shot encoder in the encoding device. The output of the single shot encoder may then be passed through quantization 325 before the encoding device sends the encoded data to a decoding device.

[0091] Accordingly, the decoding device may then perform feature decompression 330 based on receiving the encoded data. In addition, the decoding device may perform tap region feature reconstruction 335 and spatial feature reconstruction 340 to generate an output 345 (e.g., h outor h(t)). In some examples, the decoding device may perform spatial feature reconstruction 340 before performing tap domain feature reconstruction 335. After the reconstruction operation, the decoding device may output a reconstructed version via output 345 based on the input 305 from the encoding device. Using feature decompression 330, tap domain feature reconstruction 335, and spatial feature reconstruction 340 may represent performing or using a single shot encoder in the decoding device.

[0092] In some examples, the decoding device may perform operations in the opposite order to the operations performed by the encoding device. For example, if the encoding device follows operations (A, B, C, D), the decoding device may follow the inverse operations (D, C, B, A). In addition, the decoding device may perform operations that are completely symmetrical to the operations of the encoding device. The use of this symmetrical operation may reduce the amount of bits used for neural network configuration in the encoding device. Additionally or alternatively, the decoding device may perform additional operations (e.g., convolution operations, fully connected operations, ResNet operations, etc.) in addition to the operations performed by the encoding device. That is, the decoding device may perform operations that are asymmetrical to the operations of the encoding device.

[0093] Based on the encoding device encoding the data set using a neural network for uplink communication, the encoding device (e.g., UE 115) may transmit measurement results (e.g., channel condition feedback) with a reduced payload. This reduced payload may save network resources that might otherwise be used to transmit the full data set as sampled by the encoding device. As described herein with reference to FIG. 2, the encoding device may perform additional encoding operations using additional layers to further compress the data to be transmitted to the decoding device.

[0094] For example, as shown in connection with the compression procedure 301, the encoding device may apply or use a differential encoder 360, an entropy encoder 365, or both, to the output of the single shot encoder to further compress the feedback 370 transmitted to the decoding device. The feedback 370 may be an example of information transmitted over an air interface (or some other medium) between the transmitting device and the receiving device. In addition, the decoding device may also use an entropy decoder 375, a differential decoder 380, or both, before performing the single shot decoder operation described in connection with the compression procedure 300 of FIG. 3A. Additionally or alternatively, although not shown, the encoding device may apply or use a differential encoder 360 at the input stage to the single shot encoder, and the decoding device may apply or use a differential decoder 380 to the output of the single shot decoder. In some examples, the compression procedure 301 may be referred to as a time compression operation or procedure.

[0095] As shown in the example of FIG. 3B, the encoding device may take in an input 305 and pass the input 305 through an encoder neural network 350. In some examples, the encoder neural network 350 may correspond to the spatial feature extraction 310, the tap region feature extraction 315, and the feature compression 320 as described in connection with FIG. 3A (e.g., a single-shot encoder). After the input 305 passes through the encoder neural network 350, the encoding device may perform a quantization operation (e.g., the quantization 325 as described in connection with FIG. 3A) using a quantizer 355. Subsequently, the encoding device may then use or apply a differential encoder 360, an entropy encoder 365, or both to the quantized output of the encoder neural network 350. In some examples, the differential encoder 360 and the entropy encoder 365 may be performed as described with reference to FIG. 2. The encoding device may then send a feedback 370 to the decoding device, where the feedback 370 represents the encoded, quantized, and compressed data set.

[0096] The decoding device may receive the feedback 370 and may use or apply an entropy decoder 375, a differential decoder 380, or both to partially decode or decompress the encoded, quantized, compressed data set received with the feedback 370. After using or applying the entropy decoder 375, the differential decoder 380, or both, the decoding device may then pass the partially decoded and decompressed data set through a decoder neural network 385 to generate the output 345. In some examples, the decoder neural network 385 may include feature decompression 330, tap region feature reconstruction 335, and spatial feature reconstruction 340 (e.g., and any additional layers) as described in connection with FIG.

[0097] FIG. 4 illustrates an example of a compression configuration 400 supporting an encoding technique for a neural network architecture according to an aspect of the disclosure. In some examples, the compression configuration 400 may implement or be implemented by aspects of the wireless communication system 100, the wireless communication system 200, or both. For example, an encoding device (e.g., the UE 115 or an additional encoding device) may be configured to perform one or more operations on samples (e.g., data) received via one or more antennas of the encoding device to compress the samples. A decoding device (e.g., the base station 105 or an additional decoding device) may subsequently be configured to decode the compressed samples to determine information such as channel condition feedback. In some examples, the compression configuration 400 may represent an example of a channel condition feedback compression operation or procedure using entropy coding.

[0098] The encoding device may identify an input 405 for performing the compression configuration 400. For example, the input 405 may include a dataset (e.g., multiple measurements, such as channel state feedback measurements) to be compressed and encoded. In some examples, the encoding device may receive sampling from an antenna, and the input 405 represents a 64×64 dimensional dataset received from that antenna based on the amount of antennas, the amount of samples per antenna, and the tap features. The 64×64 dimensional dataset may represent one non-limiting example for the input 405. The encoding device may pass the input 405 to or through a first convolutional layer 410. For example, the first convolutional layer 410 may represent an initial layer for spatial feature extraction and short-term (tap) feature extraction using one-dimensional convolution (e.g., Conv1D). The first convolutional layer 410 (e.g., an additional convolutional layer) may be a fully connected layer (e.g., among antennas) and a simple convolution with a small kernel size (e.g., 3) in the tap dimension (to extract short tap features). The output from such a 64×W one-dimensional convolution operation may be a W×64 matrix.

[0099] After the first convolutional layer 410, the encoding device may perform one or more ResNet operations using one or more corresponding ResNet blocks, such as ResNet block 415 and ResNet block 420. The one or more ResNet operations may further refine the spatial and / or temporal features. In some examples, the ResNet operation may include multiple operations related to the features. For example, the ResNet operation may include multiple (e.g., three) one-dimensional convolution operations, a skip connection (e.g., between the input of the ResNet and the output of the ResNet to avoid applying the one-dimensional convolution operations), an addition operation of a pass through the multiple one-dimensional convolution operations and a pass through a skip connection, or an additional operation. In some examples, the multiple one-dimensional convolution operations may include a W×256 convolution operation with a kernel size of 3, the output of which is input to a batch normalization (BN) layer followed by a rectified linear unit (ReLU) activation (e.g., such as a LeakyReLU activation), which produces an output dataset of dimension 256×64, a 256×512 convolution operation with a kernel size of 3, the output of which is input to a BN layer followed by a ReLU activation, which produces an output dataset of dimension 512×64, a 512×W convolution operation with a kernel size of 3, which outputs a BN dataset of dimension W×64. The output from the one or more ResNet operations may be a W×64 matrix.

[0100] The encoding device may use additional convolutional layers 425 to perform a W×V convolution operation on the output from one or more ResNet operations. The W×V convolution operation may include a pointwise (e.g., tapwise) convolution operation. The W×V convolution operation may compress spatial features into a reduced dimension for each tap. The W×V convolution operation may have an input of W features and an output of V features. The output from the W×V convolution operation may be a V×64 matrix.

[0101] The encoding device may perform a flattening operation 430 to flatten the V×64 matrix into a 64V element vector. The encoding device may use a fully connected layer 435 to perform a 64V×M fully connected operation to further compress the spatio-temporal feature dataset into a low dimensional vector of size M for transmission over the air to the decoding device. The encoding device may perform quantization 440 prior to over the air transmission of the low dimensional vector of size M to map the transmit sampling into discrete values ​​of the low dimensional vector of size M. After quantization 440, the encoding device may use or apply an entropy encoder 445 to further compress the output of quantization 440.

[0102] The decoding device may receive entropy encoded data and may use or apply the entropy decoder 450 to decode the encoded transmission. In addition, the decoding device may perform an M×64V fully connected operation using a fully connected layer 455 to unpack the reduced dimensional vector of size M into a spatio-temporal feature dataset. The decoding device may perform a reshape operation 460 to reshape the 64V element vector into a two-dimensional V×64 matrix. The decoding device may perform a V×W (with a kernel size of 1) convolution operation using a convolution layer 465 on the output from the reshape operation 460. The V×W convolution operation may include a pointwise (e.g., tapwise) convolution operation. In some examples, the V×W convolution operation may unpack the spatial features from the reduced dimensions for each tap. The V×W convolution operation may have an input of V features and an output of W features. The output from the V×W convolution operation may be a W×64 matrix.

[0103] The decoding device may then perform one or more ResNet operations using one or more corresponding ResNet blocks, such as ResNet block 470 and ResNet block 475. The one or more ResNet operations may further decompress the spatial features, the temporal features, or both. In some examples, the ResNet operations may include multiple (e.g., three) one-dimensional convolution operations, a skip connection (e.g., to avoid applying a one-dimensional convolution operation), an addition operation of a pass through the multiple convolution operations and a pass through the skip connection, or an additional operation. The output from the one or more ResNet operations may be a W×64 matrix.

[0104] The decoding device may then perform reconstruction of spatial and temporal features using the convolutional layer 480. In some examples, reconstruction of spatial and temporal features may be achieved through the use of a one-dimensional convolution operation that is fully connected in the spatial dimension (to reconstruct spatial features) and a simple convolution with a small kernel size (e.g., 3) in the tap dimension (to reconstruct short tap features). The output from the 64×W convolution operation may be a 64×64 matrix and may be represented by output 485. In some examples, the values ​​of M, W, and / or V may be configurable to adjust feature weights, payload size, etc. Additionally, although a 64×64 dimensional dataset (e.g., a 64×64 matrix) is described in the example of FIG. 4 for corresponding operations equivalent to a 64×64 dimensional dataset, datasets of any size may be used to perform the operations described herein.

[0105] FIG. 5 illustrates an example of a compression and encoding configuration 500 supporting an encoding technique for a neural network architecture according to an aspect of the disclosure. In some examples, the compression and encoding configuration 500 may implement or be implemented by aspects of the wireless communication system 100, the wireless communication system 200, or both. For example, the encoding device (e.g., the UE 115 or an additional encoding device) may be configured to perform one or more operations on an input 505 of samples (e.g., data) received via one or more antennas of the encoding device to compress the samples. Subsequently, the decoding device (e.g., the base station 105 or an additional decoding device) may be configured to decode the compressed samples to determine an output 530 of information such as channel condition feedback based on the input 505. In some examples, the compression and encoding configuration 500 may represent a compression and encoding procedure that includes a differential encoder 510, an entropy encoder 515, or both, at the output of the encoder (e.g., a single shot encoder, an encoder neural network, etc.). By using or applying a differential encoder 510 at the output of the encoder, the encoding device can reduce or limit error propagation.

[0106] The encoding device may take an input 505 and may first encode, compress, and quantize the input 505 using one or more operations of an encoder, such as one or more convolutional layers, one or more ResNet blocks, one or more fully connected layers, and a quantizer, as described in connection with FIG. 4. After being quantized (e.g., at the output of the encoder), the encoding device may use or apply a differential encoder 510. As described in connection with FIG. 2, the differential encoder 510 may use previous values ​​of the data to encode the data. In some examples, a decoding device or a network device may indicate which previous values ​​the encoding device should use for the differential encoder 510 (e.g., via one or more parameters for the differential encoding operation). For example, the encoding device may use an initial value of the data (e.g., in an I frame) to determine a differential value for that data at a later time instance (e.g., in a P frame), may use a previous reconstructed value of the data to determine a differential value for that data at a later time instance, may use an initial reconstructed value of the data to determine a differential value for that data at a later time instance, or may be a combination thereof.

[0107] For example, when using an initial value of data to determine a difference value for that data at a later time instance, the encoding device may calculate a P subframe (e.g., a P frame) with respect to an I frame. A given difference value for a time instance (N-1) may be given by Equation 1: (x N-1 -x0) (1) x0 may represent the initial value of the data (e.g., determined in an I-frame), and x N-1 may represent a given value of that data at time N-1 (e.g., determined in a P frame). The encoding device may calculate a difference value for the data given by Equation 1 as

number

number

number

[0108] On the decryption device side, the decryption device P / D P The decoding device may then receive a representation of the data given by:

number

number

[0109] The decoding device then compares the reconstructed values ​​(e.g.,

number

number

number

[0110] Additionally or alternatively, the encoding device may use construction and reconstruction of P subframes based on a channel that is reconstructed when using or applying the differential encoder 510 (e.g., based on one or more parameters signaled to the encoding device for the differential encoder 510). Using construction and reconstruction of P subframes based on a channel that is reconstructed may reduce or prevent error propagation. In some examples, the encoding device may determine a reconstructed value for a given data value. For example, the encoding device may:

number

number

number

number

[0111] Subsequently, for a given P frame after the I frame (e.g., P Frame 1, P Frame 2, etc.), the encoding device may use the reconstructed values ​​for the previous values ​​to encode the difference values ​​for the values ​​at the given P frame. For example, for P Frame N-1 (e.g., at time N-1), the encoding device may determine the difference value for the data at time N-1 based on Equation 3.

number

[0112] The encoding device may then perform operations similar to those previously described (e.g., to calculate the difference value for the data given by Equation 3):

number

number

number

number

number

number

[0113] Thus, the decoding device may receive the encoded, quantized, compressed data set from the encoding device and may partially decode the encoded, quantized, compressed data set using the entropy decoder 520 and the differential decoder 525. In addition, the decoding device may determine and obtain an output 530 corresponding to the input 505 using one or more fully connected layers, one or more convolutional layers, and one or more ResNet blocks as described in connection with FIG.

[0114] FIG. 6 illustrates an example of a compression and encoding configuration 600 supporting an encoding technique for a neural network architecture according to an aspect of the disclosure. In some examples, the compression and encoding configuration 600 may implement or be implemented by aspects of the wireless communication system 100, the wireless communication system 200, or both. For example, an encoding device (e.g., a UE 115 or an additional encoding device) may be configured to perform one or more operations on an input 605 of samples (e.g., data) received via one or more antennas of the encoding device to compress the samples. A decoding device (e.g., a base station 105 or an additional decoding device) may then be configured to decode the compressed samples to determine an output 640 of information, such as channel condition feedback, based on the input 605. In some examples, the compression and encoding configuration 600 may represent a compression and encoding procedure that includes a differential encoder 610 at an input of an encoder (e.g., a single-shot encoder, an encoder neural network, etc.) and an entropy encoder 620 at an output of the encoder.

[0115] With the differential encoder 610, the encoding device may use an I-frame and one or more P-frames. An I-frame may occur once every N subframes, and a P-frame may occur for the remaining N-1 subframes. In some examples, the encoding device may use two neural networks for the differential encoder 610, such as a first neural network for the I-frame and a second neural network for the P-frame. The encoding device may determine initial values ​​of data in the I-frame based on the techniques described in connection with FIG. 5 (e.g.,

number

[0116] The decoding device then determines a reconstructed value for each time instance of the data based on the difference values, as described in connection with FIG.

number

number

number

number

[0117] In addition to using or applying the differential encoder 610 at the input of the encoder, the encoding device may perform a normalization operation 615 to normalize the differentially encoded data before further encoding. In addition, the decoding device may perform a normalization undo operation 630 before using or applying the differential decoder 635. In some examples, the decoding device may also include an entropy decoder 625 that decodes the output of the entropy encoder 620.

[0118] 7 illustrates an example of a process flow 700 supporting an encoding technique for a neural network architecture according to aspects of the disclosure. In some examples, process flow 700 may implement or be implemented by aspects of wireless communication system 100, wireless communication system 200, or both. For example, process flow 700 may include base station 105-b and UE 115-b, which may represent examples of corresponding base station 105 and UE 115, respectively, as described in connection with FIGS. 1-6.

[0119] In the following description of process flow 700, operations between the UE 115-b and the base station 105-b may be performed in a different order or at different times. Some operations may be omitted from the process flow 700, or other operations may be added to the process flow 700. Although the UE 115-b and the base station 105-b are shown as performing a certain amount of the operations of process flow 700, any wireless device may perform the operations shown.

[0120] At 705, the UE 115-b may receive an indication of one or more encoding operations to use to encode the compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both. For example, the UE 115-b may receive one or more parameters corresponding to the one or more encoding operations, each of the one or more parameters corresponding to a respective encoding operation of the one or more encoding operations, and the quantized compressed data set is encoded based on the one or more parameters.

[0121] At 710, the UE 115-b may encode the data set by a neural network employed in or by the UE 115-b to generate a compressed data set. At 715, the UE 115-b may quantize the compressed data set encoded by the neural network.

[0122] At 720, the UE 115-b may encode the quantized compressed data set based on receiving the indication of the one or more encoding operations. In some examples, the UE 115-b may encode the quantized compressed data set using an entropy encoding operation. For example, the entropy encoding operation may include encoding the compressed data set using one or more symbols having lengths that vary based on the probability that the symbols occur.

[0123] Additionally or alternatively, the UE 115-b may encode the quantized compressed data set using a differential encoding operation. For example, the differential encoding operation may include encoding an amount of data of the compressed data set based on a previous value for that amount of data. In some examples, the UE 115-b may determine a difference value between a first value of data in the quantized compressed data set at a first time instance and a second value of data at a second time instance after the first time instance after the first time instance after quantizing the compressed data set encoded by the neural network, the difference value being determined based on an indication of one or more encoding operations (e.g., the indication indicating an initial value that the UE 115-b should use when determining the difference value), and the quantized compressed data set being encoded based on the difference value. Additionally or alternatively, after UE 115-b quantizes the compressed data set encoded by the neural network, it may determine a difference value between a first reconstructed value of the data in the quantized compressed data set at a first time instance and a second reconstructed value of the data at a second time instance after the first time instance, where the difference value is determined based on an indication of one or more encoding operations (e.g., the indication indicates a previous reconstructed value that UE 115-b should use when determining the difference value), and the quantized compressed data set is encoded based on the difference value.

[0124] In some examples, when performing a differential encoding operation, UE 115-b may determine initial reconstructed values ​​for data in the quantized compressed data set at an initial time instance associated with encoding the data set after quantizing the compressed data set encoded by the neural network. UE 115-b may then determine difference values ​​between additional reconstructed values ​​at additional time instances after the initial time instance and the initial reconstructed values ​​for the data after quantization, where the difference values ​​are determined based on an indication of one or more encoding operations (e.g., the indication indicates an initial reconstructed value that UE 115-b should use when determining the difference values), and the quantized compressed data set is encoded based on the difference values.

[0125] At 725, after the UE 115-b encodes the compressed data set based on one or more encoding operations, it may transmit the encoded, quantized, compressed data set (e.g., the compressed and encoded data set after the single-shot encoder) to a second device (e.g., base station 105-b). In some examples, the encoded, quantized, compressed data set may include difference values ​​for the data in the data set based on initial values ​​of the data, previous reconstructed values ​​of the data, initial reconstructed values ​​of the data, or a combination thereof.

[0126] At 730, the base station 105-b may decode the encoded, quantized, compressed data set received from the UE 115-b. For example, the base station 105-b may first decode the encoded, quantized, compressed data set and generate a compressed data set based on one or more encoding operations. In addition, the base station 105-b may then decode the compressed data set by a neural network (e.g., at or utilized by the base station 105-b) and generate a data set based on decoding the encoded, quantized, compressed data set.

[0127] 8 illustrates a block diagram 800 of a device 805 supporting encoding techniques for neural network architectures according to an embodiment of the disclosure. The device 805 may be an example of an embodiment of a UE 115 as described herein. The device 805 may include a receiver 810, a transmitter 815, and a communications manager 820. The device 805 may also include a processor. Each of these components may be in communication with one another (e.g., via one or more buses).

[0128] The receiver 810 may provide a means for receiving information such as packets, user data, control information, or any combination thereof related to various information channels (e.g., control channels, data channels, information channels for coding techniques for neural network architectures). The information may be passed to other components of the device 805. The receiver 810 may utilize a single antenna or a set of multiple antennas.

[0129] The transmitter 815 may provide a means for transmitting signals generated by other components of the device 805. For example, the transmitter 815 may transmit information such as packets, user data, control information, or any combination thereof related to various information channels (e.g., control channels, data channels, information channels for coding techniques for neural network architectures). In some examples, the transmitter 815 may be collocated with the receiver 810 in a transceiver module. The transmitter 815 may utilize a single antenna or a set of multiple antennas.

[0130] The communications manager 820, the receiver 810, the transmitter 815, or various combinations or components thereof may be examples of means for performing various aspects of the encoding techniques for neural network architectures as described herein. For example, the communications manager 820, the receiver 810, the transmitter 815, or various combinations or components thereof may support a method for performing one or more of the functions described herein.

[0131] In some examples, the communications manager 820, the receiver 810, the transmitter 815, or various combinations or components thereof may be implemented in hardware (e.g., in a communications management circuit). The hardware may include a processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof configured as or otherwise supporting means for performing the functions described in this disclosure. In some examples, the processor and a memory coupled to the processor may be configured to perform one or more of the functions described herein (e.g., by executing, by the processor, instructions stored in the memory).

[0132] Additionally or alternatively, in some examples, the communications manager 820, the receiver 810, the transmitter 815, or various combinations or components thereof may be implemented in code executed by a processor (e.g., as communications management software or firmware). If implemented in code executed by a processor, the functions of the communications manager 820, the receiver 810, the transmitter 815, or various combinations or components thereof may be performed by a general purpose processor, a DSP, a central processing unit (CPU), an ASIC, an FPGA, or any combination of these or other programmable logic devices (e.g., configured as a means for performing or otherwise supporting the functions described in this disclosure).

[0133] In some examples, the communications manager 820 may be configured to perform various operations (e.g., receive, monitor, transmit) using or otherwise cooperating with the receiver 810, the transmitter 815, or both. For example, the communications manager 820 may receive information from the receiver 810, transmit information to the transmitter 815, or be integrated in combination with the receiver 810, the transmitter 815, or both to receive information, transmit information, or perform various other operations described herein.

[0134] The communications manager 820 may support wireless communications in a UE according to examples disclosed herein. For example, the communications manager 820 may be configured as or otherwise support a means for receiving an indication of one or more encoding operations to be used to encode the compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both. The communications manager 820 may be configured as or otherwise support a means for encoding a data set to generate a compressed data set by a neural network. The communications manager 820 may be configured as or otherwise support a means for quantizing a compressed data set encoded by a neural network. The communications manager 820 may be configured as or otherwise support a means for encoding a quantized compressed data set based on receiving an indication of one or more encoding operations. The communications manager 820 may be configured as or otherwise support a means for transmitting the encoded, quantized, compressed data set to a second device after encoding the compressed data set based on the one or more encoding operations.

[0135] By including or configuring the communications manager 820 according to examples described herein, the device 805 (e.g., a processor controlling or otherwise coupled to the receiver 810, the transmitter 815, the communications manager 820, or a combination thereof) may support techniques for more efficient utilization of communications resources. For example, by using differential encoder operations, entropy encoder operations, or both, the communications manager 820 may further compress the data set for transmission to the second device, thereby reducing signaling overhead and using fewer communications resources to carry the compressed data set.

[0136] 9 illustrates a block diagram 900 of a device 905 supporting encoding techniques for neural network architectures according to an embodiment of the disclosure. The device 905 may be an example of an embodiment of a device 805 or a UE 115 as described herein. The device 905 may include a receiver 910, a transmitter 915, and a communications manager 920. The device 905 may also include a processor. Each of these components may communicate with one another (e.g., via one or more buses).

[0137] The receiver 910 may provide a means for receiving information such as packets, user data, control information, or any combination thereof related to various information channels (e.g., control channels, data channels, information channels for coding techniques for neural network architectures). The information may be passed to other components of the device 905. The receiver 910 may utilize a single antenna or a set of multiple antennas.

[0138] The transmitter 915 may provide a means for transmitting signals generated by other components of the device 905. For example, the transmitter 915 may transmit information such as packets, user data, control information, or any combination thereof related to various information channels (e.g., control channels, data channels, information channels for coding techniques for neural network architectures). In some examples, the transmitter 915 may be collocated with the receiver 910 in a transceiver module. The transmitter 915 may utilize a single antenna or a set of multiple antennas.

[0139] The device 905 or various components thereof may be examples of means for performing various aspects of encoding techniques for neural network architectures as described herein. For example, the communications manager 920 may include an encoder indication component 925, a neural network encoder component 930, a quantization component 935, an encoder component 940, an encoded data set transmission component 945, or any combination thereof. The communications manager 920 may be an example of an aspect of the communications manager 820 as described herein. In some examples, the communications manager 920, or various components thereof, may be configured to perform various operations (e.g., receive, monitor, transmit) using or otherwise cooperating with the receiver 910, the transmitter 915, or both. For example, the communications manager 920 may receive information from the receiver 910, transmit information to the transmitter 915, or be integrated in combination with the receiver 910, the transmitter 915, or both to receive information, transmit information, or perform various other operations as described herein.

[0140] The communications manager 920 may support wireless communications in the UE according to examples disclosed herein. The encoder indication component 925 may be configured as or otherwise support a means for receiving an indication of one or more encoding operations to be used to encode the compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both. The neural network encoder component 930 may be configured as or otherwise support a means for encoding the data set to generate the compressed data set by a neural network. The quantization component 935 may be configured as or otherwise support a means for quantizing the compressed data set encoded by the neural network. The encoder component 940 may be configured as or otherwise support a means for encoding the quantized compressed data set based on receiving an indication of the one or more encoding operations. The encoded data transmission component 945 may be configured as or otherwise support a means for transmitting the encoded, quantized, compressed data set to a second device after encoding the compressed data set based on the one or more encoding operations.

[0141] FIG. 10 illustrates a block diagram 1000 of a communications manager 1020 supporting encoding techniques for neural network architectures according to aspects of the disclosure. The communications manager 1020 may be an example of aspects of communications manager 820, communications manager 920, or both, as described herein. The communications manager 1020 or various components thereof may be examples of means for performing various aspects of encoding techniques for neural network architectures described herein. For example, the communications manager 1020 may include an encoder indication component 1025, a neural network encoder component 1030, a quantization component 1035, an encoder component 1040, an encoded data set transmission component 1045, a differential encoder component 1050, an entropy encoder component 1055, or any combination thereof. Each of these components may be in direct or indirect communication with each other (e.g., via one or more buses).

[0142] The communications manager 1020 may support wireless communications in a UE according to examples disclosed herein. The encoder indication component 1025 may be configured as or otherwise support a means for receiving an indication of one or more encoding operations to be used to encode the compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation, or both. The neural network encoder component 1030 may be configured as or otherwise support a means for encoding the data set to generate the compressed data set by a neural network. The quantization component 1035 may be configured as or otherwise support a means for quantizing the compressed data set encoded by the neural network. The encoder component 1040 may be configured as or otherwise support a means for encoding the quantized compressed data set based on receiving an indication of the one or more encoding operations. The encoded data transmission component 1045 may be configured as or otherwise support a means for transmitting the encoded, quantized, compressed data set to a second device after encoding the compressed data set based on one or more encoding operations.

[0143] In some examples, to support receiving an indication of the one or more encoding operations, the encoder indication component 1025 may be configured as or otherwise support a means for receiving one or more parameters corresponding to the one or more encoding operations, each of the one or more parameters corresponding to a respective encoding operation of the one or more encoding operations, and the quantized and compressed data set is encoded based on the one or more parameters.

[0144] In some examples, to support encoding of the quantized compressed data set, the differential encoder component 1050 may be configured as or otherwise support a means for encoding the quantized compressed data set using a differential encoding operation after encoding the data set using a neural network.

[0145] In some examples, to support encoding of the quantized, compressed data set, the entropy encoder component 1055 may be configured as or otherwise support a means for encoding the quantized, compressed data set using an entropy encoding operation after encoding the data set using a neural network.

[0146] In some examples, to support encoding of the quantized compressed data set, the differential encoder component 1050 may be configured or otherwise support as a means for determining a differential value between a first value of data in the quantized compressed data set at an initial time instance and a second value of data at a second time instance after the initial time instance after quantizing the compressed data set to be encoded by a neural network, the differential value being determined based on an indication of one or more encoding operations, and the quantized compressed data set being encoded based on the differential value.

[0147] In some examples, to support encoding of the quantized compressed data set, the differential encoder component 1050 may be configured as or otherwise support a means for determining a differential value between a first reconstructed value of data in the quantized compressed data set at a first time instance and a second reconstructed value of the data at a second time instance after the first time instance, after quantizing the compressed data set to be encoded by the neural network, where the differential value is determined based on an indication of one or more encoding operations, and the quantized compressed data set is encoded based on the differential value.

[0148] In some examples, to support encoding of the quantized compressed data set, the differential encoder component 1050 may be configured or otherwise support as a means for determining an initial reconstruction value for data in the quantized compressed data set at an initial time instance associated with encoding the data set after quantizing the compressed data set encoded by the neural network. In some examples, to support encoding of the quantized compressed data set, the differential encoder component 1050 may be configured or otherwise support as a means for determining a difference value between an initial reconstruction value for the data and additional reconstruction values ​​of the data at additional time instances after the initial time instance after quantization, the difference value being determined based on an indication of one or more encoding operations, and the quantized compressed data set being encoded based on the difference value.

[0149] In some examples, the differential encoding operation involves encoding an amount of data in a compressed data set based on a previous value for that amount of data.

[0150] In some examples, the entropy encoding operation includes encoding the compressed data set using one or more symbols having lengths that vary based on the probability that the symbol will occur.

[0151] FIG. 11 illustrates a diagram of a system 1100 including a device 1105 supporting encoding techniques for neural network architectures according to an aspect of the disclosure. The device 1105 may be or include an example of a component of a device 805, a device 905, or a UE 115 as described herein. The device 1105 may wirelessly communicate with one or more base stations 105, a UE 115, or any combination thereof. The device 1105 may include components for two-way voice and data communication, including components for transmitting and receiving communications, such as a communications manager 1120, an input / output (I / O) controller 1110, a transceiver 1115, an antenna 1125, a memory 1130, code 1135, and a processor 1140. These components may be in electronic communication or otherwise (e.g., operatively, communicatively, functionally, electronically, electrically) coupled via one or more buses (e.g., a bus 1145).

[0152] The I / O controller 1110 may manage input and output signals for the device 1105. The I / O controller 1110 may also manage peripherals that are not integrated into the device 1105. In some cases, the I / O controller 1110 may represent a physical connection or port to an external peripheral. In some cases, the I / O controller 1110 may utilize an operating system such as iOS®, ANDROID®, MS-DOS®, MS-WINDOWS®, OS / 2®, UNIX®, LINUX®, or another known operating system. Additionally or alternatively, the I / O controller 1110 may represent or interact with a modem, keyboard, mouse, touch screen, or similar device. In some cases, the I / O controller 1110 may be implemented as part of a processor, such as the processor 1140. In some cases, a user may interact with the device 1105 through the I / O controller 1110 or through a hardware component controlled by the I / O controller 1110.

[0153] In some cases, the device 1105 may include a single antenna 1125. However, in some other cases, the device 1105 may have two or more antennas 1125, which may be capable of simultaneously transmitting or receiving multiple wireless transmissions. The transceiver 1115 may communicate bidirectionally via one or more antennas 1125, a wired link, or a wireless link, as described herein. For example, the transceiver 1115 may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. The transceiver 1115 may also include a modem for modulating packets and providing the modulated packets to the one or more antennas 1125 for transmission, and for demodulating packets received from the one or more antennas 1125. The transceiver 1115, or the transceiver 1115 and the one or more antennas 1125, may be an example of a transmitter 815, a transmitter 915, a receiver 810, a receiver 910, or any combination or components thereof, as described herein.

[0154] The memory 1130 may include random access memory (RAM) and read only memory (ROM). The memory 1130 may store computer readable, computer executable code 1135 including instructions that, when executed by the processor 1140, cause the device 1105 to perform various functions described herein. The code 1135 may be stored in a non-transitory computer readable medium, such as a system memory or another type of memory. In some cases, the code 1135 may not be directly executable by the processor 1140, but may (e.g., when compiled and executed) cause a computer to perform functions described herein. In some cases, the memory 1130 may include a basic I / O system (BIOS) that may control basic hardware or software operations, such as interaction with peripheral components or devices, among others.

[0155] The processor 1140 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, a microcontroller, an ASIC, an FPGA, a programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, or any combination thereof). In some cases, the processor 1140 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into the processor 1140. The processor 1140 may be configured to execute computer-readable instructions stored in a memory (e.g., memory 1130) to cause the device 1105 to perform various functions (e.g., functions or tasks supporting encoding techniques for neural network architectures). For example, the device 1105 or a component of the device 1105 may include a processor 1140 and a memory 1130 coupled to the processor 1140, where the processor 1140 and the memory 1130 are configured to perform various functions described herein.

[0156] The communications manager 1120 may support wireless communications in a UE according to examples disclosed herein. For example, the communications manager 1120 may be configured as or otherwise support a means for receiving an indication of one or more encoding operations to be used to encode the compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation, or both. The communications manager 1120 may be configured as or otherwise support a means for encoding a data set to generate a compressed data set by a neural network. The communications manager 1120 may be configured as or otherwise support a means for quantizing a compressed data set encoded by a neural network. The communications manager 1120 may be configured as or otherwise support a means for encoding a quantized compressed data set based on receiving an indication of one or more encoding operations. The communications manager 1120 may be configured as or otherwise support a means for transmitting the encoded, quantized, compressed data set to a second device after encoding the compressed data set based on the one or more encoding operations.

[0157] By including or configuring the communications manager 1120 according to examples described herein, the device 1105 may support techniques for more efficient utilization of communications resources, improved inter-device coordination, and improved utilization of processing power. For example, by using a differential encoder operation, an entropy encoder operation, or both, the communications manager 1120 may further compress a data set for transmission to a second device, thereby reducing signaling overhead and using fewer communications resources to convey the compressed data set. In addition, by receiving indications of parameters for different encoder operations from a network device, the communications manager 1120 may support coordination between the device 1105 and the network device. Using a differential encoder operation, an entropy encoder operation, or both may also use more of the processing power of the device 1105, rather than fewer encoding operations that would result in less compressed data than would have been obtained without the differential and entropy encoder operations.

[0158] In some examples, the communications manager 1120 may be configured to perform various operations (e.g., receive, monitor, transmit) using or otherwise cooperating with the transceiver 1115, one or more antennas 1125, or any combination thereof. Although the communications manager 1120 is shown as a separate component, in some examples, one or more functions described in connection with the communications manager 1120 may be supported or performed by the processor 1140, the memory 1130, the code 1135, or any combination thereof. For example, the code 1135 may include instructions executable by the processor 1140 to cause the device 1105 to perform various aspects of encoding techniques for neural network architectures as described herein, or the processor 1140 and the memory 1130 may be otherwise configured to perform or support such operations.

[0159] 12 illustrates a block diagram 1200 of a device 1205 supporting encoding techniques for neural network architectures according to an aspect of the disclosure. The device 1205 may be an example of an aspect of a base station 105 as described herein. The device 1205 may include a receiver 1210, a transmitter 1215, and a communications manager 1220. The device 1205 may also include a processor. Each of these components may communicate with one another (e.g., via one or more buses).

[0160] The receiver 1210 may provide a means for receiving information such as packets, user data, control information, or any combination thereof related to various information channels (e.g., control channels, data channels, information channels for coding techniques for neural network architectures). The information may be passed to other components of the device 1205. The receiver 1210 may utilize a single antenna or a set of multiple antennas.

[0161] The transmitter 1215 may provide a means for transmitting signals generated by other components of the device 1205. For example, the transmitter 1215 may transmit information such as packets, user data, control information, or any combination thereof related to various information channels (e.g., control channels, data channels, information channels for coding techniques for neural network architectures). In some examples, the transmitter 1215 may be collocated with the receiver 1210 in a transceiver module. The transmitter 1215 may utilize a single antenna or a set of multiple antennas.

[0162] The communications manager 1220, the receiver 1210, the transmitter 1215, or various combinations or components thereof may be examples of means for performing various aspects of the encoding techniques for neural network architectures as described herein. For example, the communications manager 1220, the receiver 1210, the transmitter 1215, or various combinations or components thereof may support a method for performing one or more of the functions described herein.

[0163] In some examples, the communications manager 1220, the receiver 1210, the transmitter 1215, or various combinations or components thereof may be implemented in hardware (e.g., in a communications management circuit). The hardware may include a processor, a DSP, an ASIC, an FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof configured as or otherwise supporting a means for performing the functions described in this disclosure. In some examples, the processor and a memory coupled to the processor may be configured to perform one or more of the functions described herein (e.g., by executing, by the processor, instructions stored in the memory).

[0164] Additionally or alternatively, in some examples, the communications manager 1220, the receiver 1210, the transmitter 1215, or various combinations or components thereof may be implemented in code executed by a processor (e.g., as communications management software or firmware). If implemented in code executed by a processor, the functions of the communications manager 1220, the receiver 1210, the transmitter 1215, or various combinations or components thereof may be performed by a general purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination of these or other programmable logic device (e.g., configured as a means for performing or otherwise supporting the functions described in this disclosure).

[0165] In some examples, the communications manager 1220 may be configured to perform various operations (e.g., receive, monitor, transmit) using or otherwise cooperating with the receiver 1210, the transmitter 1215, or both. For example, the communications manager 1220 may receive information from the receiver 1210, transmit information to the transmitter 1215, or be integrated in combination with the receiver 1210, the transmitter 1215, or both to receive information, transmit information, or perform various other operations as described herein.

[0166] The communications manager 1220 may support wireless communications in the device according to examples disclosed herein. For example, the communications manager 1220 may be configured as or otherwise support a means for transmitting to the UE an indication of one or more encoding operations that the UE should use to encode the compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both. The communications manager 1220 may be configured as or otherwise support a means for receiving from the UE an encoded, quantized, compressed data set after the compressed data set has been encoded following a quantization operation based on the one or more encoding operations. The communications manager 1220 may be configured as or otherwise support a means for decoding the encoded, quantized, compressed data set to generate a compressed data set based at least in part on the one or more encoding operations. The communications manager 1220 may be configured as or otherwise support a means for decoding the compressed data set to generate data based on decoding the encoded, quantized, compressed data set by a neural network.

[0167] 13 illustrates a block diagram 1300 of a device 1305 supporting encoding techniques for neural network architectures according to an aspect of the disclosure. The device 1305 may be an example of an aspect of the device 1205 or base station 105 as described herein. The device 1305 may include a receiver 1310, a transmitter 1315, and a communications manager 1320. The device 1305 may also include a processor. Each of these components may communicate with one another (e.g., via one or more buses).

[0168] The receiver 1310 may provide a means for receiving information such as packets, user data, control information, or any combination thereof related to various information channels (e.g., control channels, data channels, information channels for coding techniques for neural network architectures). The information may be passed to other components of the device 1305. The receiver 1310 may utilize a single antenna or a set of multiple antennas.

[0169] The transmitter 1315 may provide a means for transmitting signals generated by other components of the device 1305. For example, the transmitter 1315 may transmit information such as packets, user data, control information, or any combination thereof related to various information channels (e.g., control channels, data channels, information channels for coding techniques for neural network architectures). In some examples, the transmitter 1315 may be collocated with the receiver 1310 in a transceiver module. The transmitter 1315 may utilize a single antenna or a set of multiple antennas.

[0170] The device 1305 or various components thereof may be examples of means for performing various aspects of the encoding techniques for neural network architectures described herein. For example, the communications manager 1320 may include an encoding operation indication component 1325, an encoded data set receiving component 1330, a decoder component 1335, a neural network decoder component 1340, or any combination thereof. The communications manager 1320 may be an example of an aspect of the communications manager 1220 described herein. In some examples, the communications manager 1320 or various components thereof may be configured to perform various operations (e.g., receive, monitor, transmit) using or otherwise cooperating with the receiver 1310, the transmitter 1315, or both. For example, the communications manager 1320 may receive information from the receiver 1310, transmit information to the transmitter 1315, or be integrated in combination with the receiver 1310, the transmitter 1315, or both to receive information, transmit information, or perform various other operations described herein.

[0171] The communications manager 1320 may support wireless communications in the device according to examples disclosed herein. The encoding operation indication component 1325 may be configured as or otherwise support a means for transmitting an indication of one or more encoding operations to the UE to be used by the UE to encode the compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both. The encoded data set receiving component 1330 may be configured as or otherwise support a means for receiving an encoded, quantized, compressed data set from the UE after the compressed data set has been encoded following a quantization operation based on the one or more encoding operations. The decoder component 1335 may be configured as or otherwise support a means for decoding the encoded, quantized, compressed data set to generate a compressed data set based on the one or more encoding operations. The neural network decoder component 1340 may be configured as or otherwise support a means for decoding the compressed data set to generate a data set based on decoding the encoded, quantized, compressed data set by a neural network.

[0172] FIG. 14 illustrates a block diagram 1400 of a communications manager 1420 supporting encoding techniques for neural network architectures according to aspects of the disclosure. The communications manager 1420 may be an example of aspects of the communications manager 1220, the communications manager 1320, or both, as described herein. The communications manager 1420 or various components thereof may be examples of means for performing various aspects of the encoding techniques for neural network architectures described herein. For example, the communications manager 1420 may include an encoding operation indication component 1425, an encoding data set receiving component 1430, a decoder component 1435, a neural network decoder component 1440, a differential decoder component 1445, an entropy decoder component 1450, or any combination thereof. Each of these components may be in direct or indirect communication with each other (e.g., via one or more buses).

[0173] The communications manager 1420 may support wireless communications in the device according to examples disclosed herein. The encoding operation indication component 1425 may be configured as or otherwise support a means for transmitting an indication of one or more encoding operations to the UE to be used by the UE to encode the compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both. The encoded data set receiving component 1430 may be configured as or otherwise support a means for receiving an encoded, quantized, compressed data set from the UE after the compressed data set has been encoded following a quantization operation based on the one or more encoding operations. The decoder component 1435 may be configured as or otherwise support a means for decoding the encoded, quantized, compressed data set based on the one or more encoding operations to generate a compressed data set. The neural network decoder component 1440 may be configured as or otherwise support a means for decoding the compressed data set to generate a data set based on decoding the encoded, quantized, compressed data set by a neural network.

[0174] In some examples, to support transmitting an indication of the one or more encoding operations, the encoding operation indication component 1425 may be configured as or otherwise support a means for transmitting one or more parameters corresponding to the one or more encoding operations, each of the one or more parameters corresponding to a respective encoding operation of the one or more encoding operations, and the quantized and compressed data set is encoded based on the one or more parameters.

[0175] In some examples, to support decoding of the encoded, quantized, compressed data set, the differential decoder component 1445 may be configured as or otherwise support a means for decoding the encoded, quantized, compressed data set using a differential decoding operation.

[0176] In some examples, to support decoding of the encoded, quantized, compressed data set, the entropy decoder component 1450 may be configured as or otherwise support a means for decoding the encoded, quantized, compressed data set using an entropy decoding operation.

[0177] In some examples, to support receipt of the encoded, quantized, compressed data set, the differential decoder component 1445 may be configured as or otherwise support a means for receiving an encoded, quantized, compressed data set that includes differential values ​​for data in the data set that are based on an initial value of the data.

[0178] In some examples, to support receipt of an encoded, quantized, compressed data set, the differential decoder component 1445 may be configured as or otherwise support a means for receiving an encoded, quantized, compressed data set that includes differential values ​​for data in the data set that are based on previous reconstructed values ​​for the data.

[0179] In some examples, to support receipt of the encoded, quantized, compressed data set, the differential decoder component 1445 may be configured as or otherwise support a means for receiving an encoded, quantized, compressed data set that includes differential values ​​for data in the data set based on an initial reconstruction value of the data.

[0180] In some examples, the differential decoding operation involves encoding an amount of data in a compressed data set based on a previous value for that amount of data.

[0181] In some examples, the entropy decoding operation includes encoding the compressed data set using one or more symbols having lengths that vary based on the probability that the symbol will occur.

[0182] FIG. 15 illustrates a diagram of a system 1500 including a device 1505 supporting encoding techniques for neural network architectures according to an aspect of the disclosure. The device 1505 may be or include an example of a component of a device 1205, a device 1305, or a base station 105 as described herein. The device 1505 may wirelessly communicate with one or more base stations 105, UEs 115, or any combination thereof. The device 1505 may include components for two-way voice and data communication, including components for transmitting and receiving communications, such as a communications manager 1520, a network communications manager 1510, a transceiver 1515, an antenna 1525, a memory 1530, code 1535, a processor 1540, and an inter-station communications manager 1545. These components may be in electronic communication or otherwise (e.g., operatively, communicatively, functionally, electronically, electrically) coupled via one or more buses (e.g., a bus 1550).

[0183] The network communications manager 1510 may manage communications with the core network 130 (e.g., via one or more wired backhaul links). For example, the network communications manager 1510 may manage the transfer of data communications for client devices, such as one or more UEs 115.

[0184] In some cases, the device 1505 may include a single antenna 1525. However, in some other cases, the device 1505 may have two or more antennas 1525, which may be capable of simultaneously transmitting or receiving multiple wireless transmissions. The transceiver 1515 may communicate bidirectionally via one or more antennas 1525, a wired link, or a wireless link, as described herein. For example, the transceiver 1515 may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. The transceiver 1515 may also include a modem for modulating packets and providing the modulated packets to the one or more antennas 1525 for transmission, and for demodulating packets received from the one or more antennas 1525. The transceiver 1515, or the transceiver 1515 and the one or more antennas 1525, may be an example of the transmitter 1215, the transmitter 1315, the receiver 1210, the receiver 1310, or any combination or components thereof, as described herein.

[0185] The memory 1530 may include RAM and ROM. The memory 1530 may store computer-readable, computer-executable code 1535 including instructions that, when executed by the processor 1540, cause the device 1505 to perform various functions described herein. The code 1535 may be stored in a non-transitory computer-readable medium, such as a system memory or another type of memory. In some cases, the code 1535 may not be directly executable by the processor 1540, but may (e.g., when compiled and executed) cause a computer to perform functions described herein. In some cases, the memory 1530 may include a BIOS that may control basic hardware or software operations, such as interaction with peripheral components or devices, among others.

[0186] The processor 1540 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, a microcontroller, an ASIC, an FPGA, a programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, or any combination thereof). In some cases, the processor 1540 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into the processor 1540. The processor 1540 may be configured to execute computer-readable instructions stored in a memory (e.g., memory 1530) to cause the device 1505 to perform various functions (e.g., functions or tasks supporting encoding techniques for neural network architectures). For example, the device 1505 or a component of the device 1505 may include a processor 1540 and a memory 1530 coupled to the processor 1540, where the processor 1540 and the memory 1530 are configured to perform various functions described herein.

[0187] The inter-station communications manager 1545 may manage communications with other base stations 105 and may include a controller or scheduler for controlling communications with the UE 115 in cooperation with the other base stations 105. For example, the inter-station communications manager 1545 may coordinate scheduling for transmissions to the UE 115 for various interference mitigation techniques, such as beamforming or joint transmission. In some examples, the inter-station communications manager 1545 may provide an X2 interface in LTE / LTE-A wireless communications network technology to communicate between the base stations 105.

[0188] The communications manager 1520 may support wireless communications in the device according to examples disclosed herein. For example, the communications manager 1520 may be configured as or otherwise support a means for transmitting to the UE an indication of one or more encoding operations that the UE should use to encode the compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both. The communications manager 1520 may be configured as or otherwise support a means for receiving from the UE an encoded, quantized, compressed data set after the compressed data set has been encoded following a quantization operation based on the one or more encoding operations. The communications manager 1520 may be configured as or otherwise support a means for decoding the encoded, quantized, compressed data set to generate a compressed data set based at least in part on the one or more encoding operations. The communications manager 1520 may be configured as or otherwise support a means for decoding the compressed data set to generate a data set based on decoding the encoded, quantized, compressed data set by a neural network.

[0189] In some examples, the communications manager 1520 may be configured to perform various operations (e.g., receive, monitor, transmit) using or otherwise cooperating with the transceiver 1515, one or more antennas 1525, or any combination thereof. Although the communications manager 1520 is shown as a separate component, in some examples, one or more functions described in connection with the communications manager 1520 may be supported or performed by the processor 1540, the memory 1530, the code 1535, or any combination thereof. For example, the code 1535 may include instructions executable by the processor 1540 to cause the device 1505 to perform various aspects of encoding techniques for neural network architectures as described herein, or the processor 1540 and the memory 1530 may be otherwise configured to perform or support such operations.

[0190] FIG. 16 illustrates a flowchart illustrating a method 1600 for supporting encoding techniques for neural network architectures according to aspects of the disclosure. The operations of the method 1600 may be performed by a UE or components thereof as described herein. For example, the operations of the method 1600 may be performed by a UE 115 as described with reference to FIGS. 1 through 11. In some examples, the UE may execute a set of instructions to control functional elements of the UE to perform the described functions. Additionally or alternatively, the UE may perform aspects of the described functions using dedicated hardware.

[0191] At 1605, the method may include receiving an indication of one or more encoding operations to be used to encode the compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both. The operations of 1605 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1605 may be performed by an encoder indication component 1025 as described with reference to FIG.

[0192] At 1610, the method may include encoding the dataset by a neural network to generate a compressed dataset. The operations of 1610 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1610 may be performed by a neural network encoder component 1030 as described with reference to FIG.

[0193] At 1615, the method may include quantizing the compressed data set encoded by the neural network. The operations of 1615 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1615 may be performed by a quantization component 1035 as described with reference to FIG.

[0194] At 1620, the method may include encoding the quantized compressed data set based on receiving an indication of one or more encoding operations. The operations of 1620 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1620 may be performed by an encoder component 1040 as described with reference to FIG.

[0195] At 1625, the method may include transmitting the encoded, quantized, compressed data set to the second device after encoding the compressed data set based on the one or more encoding operations. The operations of 1625 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1625 may be performed by an encoded data set transmission component 1045 as described with reference to FIG.

[0196] FIG. 17 illustrates a flowchart illustrating a method 1700 for supporting encoding techniques for neural network architectures according to aspects of the disclosure. The operations of the method 1700 may be performed by a UE or components thereof as described herein. For example, the operations of the method 1700 may be performed by a UE 115 as described with reference to FIGS. 1-11. In some examples, the UE may execute a set of instructions to control functional elements of the UE to perform the described functions. Additionally or alternatively, the UE may perform aspects of the described functions using dedicated hardware.

[0197] At 1705, the method may include receiving an indication of one or more encoding operations to be used to encode the compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both. The operations of 1705 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1705 may be performed by an encoder indication component 1025 as described with reference to FIG.

[0198] At 1710, the method may include encoding the dataset by a neural network to generate a compressed dataset. The operations of 1710 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1710 may be performed by a neural network encoder component 1030 as described with reference to FIG.

[0199] At 1715, the method may include quantizing the compressed data set encoded by the neural network. The operations of 1715 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1715 may be performed by the quantization component 1035 as described with reference to FIG.

[0200] At 1720, the method may include encoding the quantized compressed data set based on receiving an indication of one or more encoding operations. The operations of 1720 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1720 may be performed by the encoder component 1040 as described with reference to FIG.

[0201] At 1725, the method may include encoding the quantized compressed data set using a differential encoding operation. The operations of 1725 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1725 may be performed by a differential encoder component 1050 as described with reference to FIG.

[0202] At 1730, the method may include transmitting the encoded, quantized, compressed data set to the second device after encoding the compressed data set based on the one or more encoding operations. The operations of 1730 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1730 may be performed by the encoded data set transmission component 1045 as described with reference to FIG.

[0203] FIG. 18 illustrates a flowchart illustrating a method 1800 for supporting encoding techniques for neural network architectures according to aspects of the disclosure. The operations of the method 1800 may be performed by a UE or components thereof as described herein. For example, the operations of the method 1800 may be performed by a UE 115 as described with reference to FIGS. 1-11. In some examples, the UE may execute a set of instructions to control functional elements of the UE to perform the described functions. Additionally or alternatively, the UE may perform aspects of the described functions using dedicated hardware.

[0204] At 1805, the method may include receiving an indication of one or more encoding operations to be used to encode the compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both. The operations of 1805 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1805 may be performed by an encoder indication component 1025 as described with reference to FIG.

[0205] At 1810, the method may include encoding the dataset by a neural network to generate a compressed dataset. The operations of 1810 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1810 may be performed by a neural network encoder component 1030 as described with reference to FIG.

[0206] At 1815, the method may include quantizing the compressed data set encoded by the neural network. The operations of 1815 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1815 may be performed by a quantization component 1035 as described with reference to FIG.

[0207] At 1820, the method may include encoding the quantized compressed data set based on receiving an indication of one or more encoding operations. The operations of 1820 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1820 may be performed by an encoder component 1040 as described with reference to FIG.

[0208] At 1825, the method may include encoding the quantized and compressed data set using an entropy encoding operation. The operations of 1825 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1825 may be performed by an entropy encoder component 1055 as described with reference to FIG.

[0209] At 1830, the method may include transmitting the encoded, quantized, compressed data set to the second device after encoding the compressed data set based on the one or more encoding operations. The operations of 1830 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1830 may be performed by an encoded data set transmission component 1045 as described with reference to FIG.

[0210] FIG. 19 illustrates a flowchart illustrating a method 1900 for supporting encoding techniques for neural network architectures according to aspects of the disclosure. The operations of the method 1900 may be performed by a base station or components thereof as described herein. For example, the operations of the method 1900 may be performed by a base station 105 as described with reference to FIGS. 1-7 and 12-15. In some examples, the base station may execute a set of instructions to control functional elements of the base station to perform the described functions. Additionally or alternatively, the base station may perform aspects of the described functions using dedicated hardware.

[0211] At 1905, the method may include transmitting to the UE an indication of one or more encoding operations that the UE should use to encode the compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both. The operations of 1905 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1905 may be performed by an encoding operation indication component 1425 as described with reference to FIG.

[0212] At 1910, the method may include receiving, from the UE, an encoded, quantized, and compressed data set after the compressed data set is encoded following a quantization operation based on one or more encoding operations. The operations of 1910 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1910 may be performed by an encoded data set receiving component 1430 as described with reference to FIG. 14.

[0213] At 1915, the method may include decoding the encoded, quantized, compressed data set to generate a compressed data set based on the one or more encoding operations. The operations of 1915 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1915 may be performed by a decoder component 1435 as described with reference to FIG. 14.

[0214] At 1920, the method may include decoding the compressed data set to generate a data set based on decoding the encoded, quantized, compressed data set by a neural network. The operations of 1920 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1920 may be performed by a neural network decoder component 1440 as described with reference to FIG. 14.

[0215] FIG. 20 illustrates a flow chart illustrating a method 2000 for supporting encoding techniques for neural network architectures according to aspects of the disclosure. The operations of method 2000 may be performed by a base station or components thereof as described herein. For example, the operations of method 2000 may be performed by base station 105 as described with reference to FIGS. 1-7 and 12-15. In some examples, the base station may execute a set of instructions to control functional elements of the base station to perform the described functions. Additionally or alternatively, the base station may perform aspects of the described functions using dedicated hardware.

[0216] At 2005, the method may include transmitting to the UE an indication of one or more encoding operations that the UE should use to encode the compressed data set, the one or more encoding operations including a differential encoding operation or an entropy encoding operation or both. The operations of 2005 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 2005 may be performed by an encoding operation indication component 1425 as described with reference to FIG.

[0217] At 2010, the method may include transmitting one or more parameters corresponding to one or more encoding operations, each of the one or more parameters corresponding to a respective encoding operation of the one or more encoding operations, and the quantized and compressed data set being encoded based on the one or more parameters. The operations of 2010 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 2010 may be performed by an encoding operation indication component 1425 as described with reference to FIG. 14.

[0218] At 2015, the method may include receiving, from the UE, an encoded, quantized, and compressed data set after the compressed data set is encoded following a quantization operation based on one or more encoding operations. The operations of 2015 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 2015 may be performed by an encoded data set receiving component 1430 as described with reference to FIG. 14.

[0219] At 2020, the method may include decoding the encoded, quantized, compressed data set to generate a compressed data set based on one or more encoding operations. The operations of 2020 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 2020 may be performed by a decoder component 1435 as described with reference to FIG. 14.

[0220] At 2025, the method may include decoding the compressed dataset by a neural network to generate a dataset based on decoding the encoded, quantized, compressed dataset. The operations of 2025 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 2025 may be performed by a neural network decoder component 1440 as described with reference to FIG. 14.

[0221] The following provides a summary of aspects of the disclosure.

[0222] Aspect 1: A method for wireless communication in a UE, the method comprising: receiving an indication of one or more encoding operations to be used to encode a compressed data set, the one or more encoding operations comprising a differential encoding operation or an entropy encoding operation or both; encoding the data set by a neural network to generate a compressed data set; quantizing the compressed data set encoded by the neural network; encoding the quantized compressed data set based at least in part on receiving the indication of the one or more encoding operations; and transmitting the encoded, quantized, compressed data set to a second device after encoding the compressed data set based at least in part on the one or more encoding operations.

[0223] Aspect 2: The method of aspect 1, wherein the step of receiving an indication of the one or more encoding operations comprises the step of receiving one or more parameters corresponding to the one or more encoding operations, each of the one or more parameters corresponding to a respective encoding operation of the one or more encoding operations, and the quantized compressed data set is encoded based at least in part on the one or more parameters.

[0224] Aspect 3: The method of any of aspects 1 to 2, wherein encoding the quantized, compressed data set comprises encoding the data set using a neural network followed by encoding the quantized, compressed data set using a differential encoding operation.

[0225] Aspect 4: The method of any of aspects 1 to 3, wherein encoding the quantized, compressed data set comprises encoding the data set using a neural network followed by encoding the quantized, compressed data set using an entropy coding operation.

[0226] Aspect 5: The method of any of aspects 1 to 4, wherein the step of encoding the quantized compressed data set comprises determining, after quantizing the compressed data set to be encoded by a neural network, a difference value between a first value of data in the quantized compressed data set at an initial time instance and a second value of data at a second time instance after the initial time instance, wherein the difference value is determined based at least in part on an indication of one or more encoding operations, and the quantized compressed data set is encoded based at least in part on the difference value.

[0227] Aspect 6: The method of any of aspects 1 to 5, wherein the step of encoding the quantized compressed data set comprises determining, after quantizing the compressed data set to be encoded by a neural network, a difference value between a first reconstruction value of data in the quantized compressed data set at a first time instance and a second reconstruction value of the data at a second time instance after the first time instance, wherein the difference value is determined based at least in part on an indication of one or more encoding operations, and the quantized compressed data set is encoded based at least in part on the difference value.

[0228] Aspect 7: The method of any of aspects 1 to 6, wherein the step of encoding the quantized compressed data set comprises: determining, after quantizing the compressed data set to be encoded by a neural network, an initial reconstruction value of data in the quantized compressed data set at an initial time instance relevant to encoding the data set; and determining, after quantization, a difference value between an additional reconstruction value of the data at an additional time instance after the initial time instance and the initial reconstruction value of the data, wherein the difference value is determined based at least in part on an indication of the one or more encoding operations, and the quantized compressed data set is encoded based at least in part on the difference value.

[0229] Aspect 8: The method of any of aspects 1-7, wherein the differential encoding operation comprises encoding an amount of data of the compressed data set based at least in part on a previous value for that amount of data.

[0230] Aspect 9: The method of any of aspects 1-8, wherein the entropy encoding operation comprises encoding the compressed data set using one or more symbols having lengths that vary based at least in part on a probability that the symbol occurs.

[0231] Aspect 10: A method for wireless communication in a device, the method comprising: transmitting to a UE an indication of one or more encoding operations to be used by the UE to encode a compressed data set, the one or more encoding operations comprising a differential encoding operation or an entropy encoding operation or both; receiving from the UE an encoded, quantized, compressed data set after the compressed data set has been encoded following a quantization operation based at least in part on the one or more encoding operations; decoding the encoded, quantized, compressed data set to generate a compressed data set based at least in part on the one or more encoding operations; and decoding the compressed data set to generate a data set based at least in part on decoding the encoded, quantized, compressed data set by a neural network.

[0232] Aspect 11: The method of aspect 10, wherein the step of transmitting an indication of the one or more encoding operations comprises the step of transmitting one or more parameters corresponding to the one or more encoding operations, each of the one or more parameters corresponding to a respective encoding operation of the one or more encoding operations, and the quantized compressed data set is encoded based at least in part on the one or more parameters.

[0233] Aspect 12: The method of any of aspects 10-11, wherein decoding the encoded, quantized, compressed data set comprises decoding the encoded, quantized, compressed data set using a differential decoding operation prior to decoding the data set using a neural network.

[0234] Aspect 13: The method of any of aspects 10 to 12, wherein decoding the encoded, quantized, compressed data set comprises decoding the encoded, quantized, compressed data set using an entropy decoding operation prior to decoding the data set using a neural network.

[0235] Aspect 14: The method of any of aspects 10 to 13, wherein receiving the encoded, quantized, compressed data set comprises receiving the encoded, quantized, compressed data set comprising difference values ​​for the data in the data set that are based at least in part on initial values ​​of the data.

[0236] Aspect 15: The method of any of aspects 10 to 14, wherein receiving the encoded, quantized, compressed data set comprises receiving an encoded, quantized, compressed data set comprising difference values ​​for data in the data set that are based at least in part on previous reconstruction values ​​of the data.

[0237] Aspect 16: The method of any of aspects 10 to 15, wherein receiving the encoded, quantized, compressed data set comprises receiving an encoded, quantized, compressed data set comprising difference values ​​for data in the data set that are based at least in part on initial reconstruction values ​​of the data.

[0238] Aspect 17: The method of any of aspects 10-16, wherein the differential decoding operation comprises encoding an amount of data of the compressed data set based at least in part on a previous value for that amount of data.

[0239] Aspect 18: The method of any of aspects 10 to 17, wherein the entropy decoding operation comprises encoding the compressed data set using one or more symbols having lengths that vary based at least in part on the probability of the symbols occurring.

[0240] Aspect 19: An apparatus for wireless communication in a UE, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform any of the methods of aspects 1 to 9.

[0241] Aspect 20: An apparatus for wireless communication in a UE, comprising at least one means for performing the method of any of aspects 1 to 9.

[0242] Aspect 21: A non-transitory computer-readable medium storing code for wireless communication in a UE, the code comprising instructions executable by a processor to perform the method of any of aspects 1 to 9.

[0243] Aspect 22: An apparatus for wireless communication in a device, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform any of the methods of aspects 10 to 18.

[0244] Aspect 23: An apparatus for wireless communication in a device, comprising at least one means for performing the method of any of aspects 10 to 18.

[0245] Aspect 24: A non-transitory computer-readable medium storing code for wireless communication in a device, the code comprising instructions executable by a processor to perform the method of any of aspects 10 to 18.

[0246] It should be noted that the methods described herein describe possible implementations, and that the acts and steps may be rearranged or otherwise modified, and that other implementations are possible. Additionally, aspects from two or more of these methods may be combined.

[0247] Although aspects of LTE, LTE-A, LTE-A Pro, or NR systems may be described as examples, and LTE, LTE-A, LTE-A Pro, or NR terminology may be used throughout much of the description, the techniques described herein may be applicable to other than LTE, LTE-A, LTE-A Pro, or NR networks. For example, the techniques described may be applicable to various other wireless communication systems, such as Ultra Mobile Broadband (UMB), Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, Flash-OFDM, and other systems and radio technologies not explicitly mentioned herein.

[0248] The information and signals described herein may be represented using any of a wide variety of technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referred to throughout the description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0249] The various example blocks and components described with respect to the disclosure herein may be implemented or performed using a general purpose processor, a DSP, an ASIC, a CPU, an FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but alternatively, the processor may be any processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration).

[0250] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. When implemented in software executed by a processor, the functions may be stored on or transmitted over a computer-readable medium as one or more instructions or codes. Other examples and implementations are within the scope of this disclosure and the appended claims. For example, due to the nature of software, the functions described herein may be implemented using software executed by a processor, hardware, firmware, hardwiring, or any combination thereof. Features implementing the functions may also be physically located in various locations, including being distributed such that parts of the functions are implemented in different physical locations.

[0251] Computer-readable media includes both non-transitory computer storage media and communication media, including any medium that enables transfer of a computer program from one place to another. Non-transitory storage media may be any available medium that can be accessed by a general purpose or special purpose computer. By way of example and not limitation, non-transitory computer-readable media may include RAM, ROM, Electrically Erasable Programmable ROM (EEPROM), Flash memory, Compact Disk (CD) ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to carry or store desired program code means in the form of instructions or data structures and that can be accessed by a general purpose or special purpose computer or a general purpose or special purpose processor. Also, any connection is properly termed a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included within the definition of computer-readable media. As used herein, disk and disc include CDs, laser discs, optical discs, digital versatile discs (DVDs), floppy disks, and Blu-ray discs, where disks typically reproduce data magnetically and discs reproduce data optically using lasers. Combinations of the above are also included within the scope of computer readable media.

[0252] As used herein, including within the claims, "or" as used in a list of items (e.g., a list of items beginning with a phrase such as "at least one of" or "one or more of") indicates an inclusive list, such as, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Also, the phrase "based on" as used herein should not be construed as a reference to a closed set of conditions. For example, an exemplary step described as "based on condition A" may be based on both condition A and condition B without departing from the scope of the present disclosure. In other words, the phrase "based on" as used herein is to be construed similarly to the phrase "based at least in part on."

[0253] The terms "determine" or "determining" encompass a wide variety of actions, and thus "determining" can include calculating, computing, processing, deriving, investigating, looking up (e.g., looking in a table, database, or another data structure), ascertaining, and the like. Also, "determining" can include receiving (such as receiving information), accessing (accessing data in a memory), and the like. Also, "determining" can include resolving, selecting, choosing, establishing, or other such similar actions.

[0254] In the accompanying figures, similar components or features may have the same reference label. Furthermore, various components of the same type may be distinguished by following the reference label with a dash and a second label that distinguishes the similar components. If only a first reference label is used herein, the description is applicable to any of the similar components having the same first reference label, regardless of the second reference label, or any other subsequent reference label.

[0255] The description set forth herein with respect to the accompanying drawings describes exemplary configurations and does not necessarily represent all examples that may be implemented or fall within the scope of the claims. As used herein, the term "exemplary" means "serving as an example, instance, or illustration" and does not mean "preferred" or "advantageous over other examples." The detailed description includes specific details for the purposes of providing an understanding of the described techniques. However, these techniques may be practiced without these specific details. In some instances, known structures and devices are shown in block diagram form to avoid obscuring the concepts of the described examples.

[0256] The description herein is provided to enable any person skilled in the art to make or use the disclosure. Various modifications of the disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein, but should be accorded the widest scope consistent with the principles and novel features disclosed herein. [Explanation of symbols]

[0257] 105 Base station 110 Coverage Area 115 UE 120 backhaul links 125 Communication Links 130 Core Network 135 D2D communication links 140 Access Network Entity 145 Access Network Transmission Entity 150 IP Services 200 Wireless Communication System 205 Career 210 Career 215 Encoding parameters 220 Differential Encoder Parameters 225 Entropy Encoder Parameters 230 Dataset to be compressed and encoded 235 Compressed and Encoded Data Sets 305 Input 310 Spatial Feature Extraction 315 Tap Area Feature Extraction 320 Feature Compression 325 Quantization 330 Feature Extraction 335 Tap Area Feature Reconstruction 340 Spatial Feature Reconstruction 345 Output 350 Encoder Neural Network 355 Quantizer 360 Differential Encoder 365 Entropy Encoder 370 Feedback 375 Entropy Decoder 380 Differential Decoder 385 Decoder Neural Network 405 Input 410 Convolutional Layer 415 ResNet blocks 420 ResNet blocks 425 Convolutional Layer 430 Flattening operation 435 Fully connected layer 440 Quantization 445 Entropy Encoder 450 Entropy Decoder 455 Fully connected layer 460 Reshaping operation 465 Convolutional Layer 470 ResNet blocks 475 ResNet blocks 480 convolutional layers 485 Output 505 Input 510 Differential Encoder 515 Entropy Encoder 520 Entropy Decoder 525 Differential Decoder 530 Output 605 Input 610 Differential Encoder 615 Normalization operation 620 Entropy Encoder 625 Entropy Decoder 630 Normalization Cancellation Operation 635 Differential Decoder 640 Output 805 Devices 810 Receiver 815 Transmitter 820 Communications Manager 905 Devices 910 Receiver 915 Transmitter 920 Communications Manager 925 Encoder Indication Components 930 Neural Network Encoder Component 935 Quantized Components 940 Encoder Component 945 Encoded Data Set Transmission Component 1020 Communications Manager 1025 Encoder Indication Component 1030 Neural Network Encoder Component 1035 Quantization Component 1040 Encoder Component 1045 Encoded Data Set Transmission Component 1050 Differential Encoder Component 1055 Entropy Encoder Component 1105 Devices 1110 I / O Controller 1115 Transceiver 1120 Communications Manager 1125 Antenna 1130 Memory 1135 Code 1140 Processor 1145 Bus 1205 Devices 1210 Receiver 1215 Transmitter 1220 Communications Manager 1305 Devices 1310 Receiver 1315 Transmitter 1320 Communications Manager 1325 Encoding Operation Indicator Component 1330 Encoded Data Set Reception Component 1335 Decoder Component 1340 Neural Network Decoder Component 1420 Communications Manager 1425 Encoding Operation Indicator Component 1430 Encoded Data Set Reception Component 1435 Decoder Component 1440 Neural Network Decoder Component 1445 Differential Decoder Component 1450 Entropy Decoder Component 1505 Devices 1510 Network Communications Manager 1515 Transceiver 1520 Communications Manager 1525 Antenna 1530 Memory 1535 Code 1540 Processor 1545 Inter-Station Communication Manager 1550 Bus

Claims

1. 1. A method for wireless communication in a user equipment (UE), comprising: receiving an indication of one or more encoding operations to be used to encode the compressed data set, the one or more encoding operations comprising a differential encoding operation; encoding the dataset by a neural network to generate the condensed dataset; quantizing the compressed data set encoded by the neural network; encoding the compressed quantized data set using the differential encoding operation based at least in part on receiving the indication of the one or more encoding operations; encoding the compressed, quantized, encoded data set based at least in part on the one or more encoding operations, and then transmitting the compressed, quantized, encoded data set to a second device. A method comprising:

2. receiving the indication of the one or more encoding operations, 2. The method of claim 1, comprising receiving one or more parameters corresponding to the one or more encoding operations, each of the one or more parameters corresponding to a respective encoding operation of the one or more encoding operations, and wherein the compressed quantized data set is encoded based at least in part on the one or more parameters.

3. 4. The method of claim 3, further comprising:

2. The method of claim 1, comprising determining, after quantizing the compressed data set encoded by the neural network, a difference value between a first value of data in the compressed quantized data set at an initial time instance and a second value of the data at a second time instance after the initial time instance, wherein the difference value is determined based at least in part on the indication of the one or more encoding operations, and the compressed quantized data set is encoded based at least in part on the difference value.

4. 4. The method of claim 3, further comprising:

2. The method of claim 1, comprising determining, after quantizing the compressed data set encoded by the neural network, a difference value between a first reconstruction of data in the compressed quantized data set at a first time instance and a second reconstruction of the data at a second time instance after the first time instance, wherein the difference value is determined based at least in part on the indication of the one or more encoding operations, and the compressed quantized data set is encoded based at least in part on the difference value.

5. 4. The method of claim 3, further comprising: quantizing the compressed data set encoded by the neural network, and then determining initial reconstruction values ​​for data in the compressed and quantized data set at an initial time instance associated with encoding the data set; 2. The method of claim 1, further comprising: after the quantization, determining difference values ​​between the initial reconstructed value for the data and additional reconstructed values ​​of the data at additional time instances after the initial time instance, wherein the difference values ​​are determined based at least in part on the indication of the one or more encoding operations, and wherein the compressed quantized data set is encoded based at least in part on the difference values.

6. The method of claim 1 , wherein the differential encoding operation comprises encoding an amount of data based at least in part on a previous value for the amount of data of the compressed data set.

7. 1. A method for wireless communication in a device, comprising: transmitting to a user equipment (UE) an indication of one or more encoding operations that the UE should use to encode the compressed data set, the one or more encoding operations comprising a differential encoding operation; receiving, from the UE, a compressed, quantized, and encoded data set after the compressed data set is encoded following a quantization operation based at least in part on the one or more encoding operations; decoding the compressed, quantized, encoded data set using a differential decoding operation to generate a compressed data set based at least in part on the one or more encoding operations; and decoding, by a neural network, the compressed data set to generate a data set based at least in part on decoding the compressed, quantized, encoded data set.

8. transmitting the indication of the one or more encoding operations, 8. The method of claim 7, comprising transmitting one or more parameters corresponding to the one or more encoding operations, each of the one or more parameters corresponding to a respective encoding operation of the one or more encoding operations, and wherein the compressed quantized data set is encoded based at least in part on the one or more parameters.

9. Decoding the compressed, quantized, encoded data set comprises:

8. The method of claim 7, comprising decoding the compressed, quantized, encoded data set using an entropy decoding operation prior to decoding the data set using the neural network.

10. receiving the compressed, quantized and encoded data set, 8. The method of claim 7, comprising receiving the compressed, quantized, encoded data set comprising difference values ​​for the data in the data set that are based at least in part on initial values ​​of data in the data set.

11. receiving the compressed, quantized and encoded data set, 8. The method of claim 7, comprising receiving the compressed, quantized, encoded data set comprising difference values ​​for the data in the data set that are based at least in part on previous reconstruction values ​​of data in the data set.

12. receiving the compressed, quantized and encoded data set, 8. The method of claim 7, comprising receiving the compressed, quantized, encoded data set comprising difference values ​​for the data in the data set that are based at least in part on initial reconstruction values ​​of data in the data set.

13. An apparatus for wireless communication in a user equipment (UE), comprising: A processor; a memory coupled to the processor; and instructions stored in the memory, the instructions causing the device to: receiving an indication of one or more encoding operations to be used to encode the compressed data set, the one or more encoding operations comprising a differential encoding operation; encoding the dataset by a neural network to generate the condensed dataset; quantizing the compressed data set encoded by the neural network; encoding the compressed quantized data set using the differential encoding operation based at least in part on receiving the indication of the one or more encoding operations; and encoding the compressed, quantized, encoded data set based at least in part on the one or more encoding operations, and then transmitting the compressed, quantized, encoded data set to a second device. The apparatus is executable by the processor to cause the apparatus to perform the steps of:

14. An apparatus for wireless communication in a device, comprising: A processor; a memory coupled to the processor; and instructions stored in the memory, the instructions causing the device to: transmitting, to a user equipment (UE), an indication of one or more encoding operations that the UE should use to encode a compressed data set, the one or more encoding operations comprising a differential encoding operation; receiving, from the UE, a compressed, quantized, and encoded data set after the compressed data set is encoded following a quantization operation based at least in part on the one or more encoding operations; decoding the compressed, quantized, encoded data set using a differential decoding operation to generate a compressed data set based at least in part on the one or more encoding operations; decoding, by a neural network, the compressed data set to generate a data set based at least in part on decoding the compressed, quantized, encoded data set; The apparatus is executable by the processor to cause the apparatus to perform the steps of:

15. A computer program comprising instructions, The instructions, when executed by an apparatus for wireless communication in a user equipment (UE), cause the apparatus to perform a method according to any one of claims 1 to 6, A computer program product comprising instructions which, when executed by an apparatus for wireless communication in a device, cause the apparatus to perform the method of any one of claims 7 to 12.

Images