215 results about "Neural network system" patented technology

A neural network system is provided. The system includes an autoencoder configured to encode input data into a latent space representation; a generator neural network configured to receive a noise vector and the latent space representation and output a set of routing coefficients; a discriminator neural network configured to evaluate the effectiveness of the routing coefficients by measuring the performance of a capsule network utilizing said routing coefficients; and a capsule network comprising a first capsule layer and a second capsule layer, wherein the routing coefficients are used to dynamically route outputs from the first capsule layer to the second capsule layer.

A method is provided for processing data in a neural network system. The method includes receiving input data; processing the input data through a first set of neural network layers configured to perform data processing using MatMul-free techniques to produce intermediate data; further processing the intermediate data through a second set of neural network layers configured to simulate spiking neural network (SNN) functionalities using MatMul-free techniques; and outputting a result based on the processed data from the second set of neural network layers.

Systems and methods for performing image modification. In particular, the system can, using a rectified flow neural network, perform an image inversion and image editing process to generate a modified image that has been modified according to a conditioning input received by the system.

The invention relates to the technical field of geological early warning, in particular to a dangerous rock mass instability analysis method, system and equipment based on a space-time diagram neural network, by fusing unmanned aerial vehicle LiDAR, multispectral data, meteorological radar data and the space-time diagram neural network (ST-GNN), the system realizes sub-meter spatial resolution and minute-level time response, and the stability of dangerous rock mass instability analysis is improved. The four-dimensional (time and space) analysis result of the instability probability of the dangerous rock mass is obtained through high-precision space-time modeling, the problems that a traditional geological disaster early warning system is low in resolution ratio, slow in response and high in misinformation are solved, the comprehensiveness, accuracy and reliability of instability prediction of the dangerous rock mass are improved, and the early warning effect is good. And full-chain intelligent closed-loop management of real-time data acquisition-dynamic prediction-early warning push-feedback optimization is supported, the emergency decision time is shortened by real-time rainfall superposition risk thermodynamic diagrams, and the attenuation rate of long-term prediction precision is reduced by dynamically fusing newly added geological data and instability events through incremental learning.

Systems and techniques are described herein for training and using a machine-learning model (e.g., a neural network). For example, a computing device can: process, using a first trained neural network, data specific to a user to obtain intermediate activation data representing the data, the first trained neural network comprising a plurality of neural network layers; process, using a second trained neural network, the intermediate activation data to generate an output representing the data, the second trained neural network comprising a subset of neural network layers from the plurality of neural network layers of the first trained neural network; determine a loss based on the output; and update parameters of the second trained neural network based on the loss.

A computer-implemented method for training an anomaly detection neural network system comprising an encoder and a decoder is described. The method includes receiving training data comprising a plurality of training examples, each training example including a training audio waveform and a machine identity (ID); processing the training audio waveform to extract training audio features; receiving an environmental noise audio waveform; processing the environmental noise audio waveform to extract noise features; generating augmented features by combining the extracted training audio features and the noise features; processing, using the encoder, the augmented features to generate latent embeddings; processing, using the decoder, the latent embeddings to generate reconstructed audio features; processing, using a convolutional neural network, the augmented features to generate a predicted machine ID probability distribution; and adjusting, through backpropagation, the current values of the parameters of the encoder and the decoder to minimize an objective function.

Systems and method are provided that are directed to tuning a hyperparameter associated with a small neural network model and transferring the hyperparameter to a large neural network model. At least one neural network model may be received along with a request for one or more tuned hyperparameters. Prior to scaling the large neural network, the large neural network is parameterized in accordance with a parameterizing scheme. The large neural network is then scaled and reduced in size such that a hyperparameter tuning process may be performed. A tuned hyperparameter may then be provided to a requestor such that the hyperparameter can be directly input into the large neural network. By tuning a hyper parameter using a small neural network, significant computation cycles and energy may be saved.

A RELU neuron chip circuit belongs to the field of chip circuits, and is characterized by comprising a vector summation circuit, a shift circuit, a subtraction circuit, a logic judgment circuit, an input port and an output port, the input ports comprise a data input port, a weight input port, a bias data input port and a data counting port; the output port comprises a data output port and a logic output port; by directly realizing the function of the neurons on the chip circuit, when a neural network system calls a certain neuron to carry out corresponding function calculation, data input and output can be directly carried out at the bottommost circuit level, so that a large amount of data cross-layer conversion time is saved. Only after the whole neural network completes one time of complete training or judgment operation, the operation result of the bottom layer circuit can be transmitted to the high layer from the bottom layer circuit in a cross-layer mode and displayed in a human eye recognizable mode. Therefore, the overall operation performance of the neural network system is improved.

For neural network acceleration, a datapath can be configured to implement a convolution computation. A control unit can be configured to coordinate operations of the datapath to implement the convolution computation based on coded instructions representative of a neural network system. The control unit can be configured to command the datapath to convolve at least one input feature element of a set of input feature elements of at least one input feature map with at least one discretized weight of a set of discretized weights to compute an influence that the at least one input feature element of the set of input feature elements of the least one input feature map has on one or more output feature elements of at least one output feature map.

Simulation and validation of neural network systems is provided. In various embodiments, a description of an artificial neural network is read. A directed graph is constructed comprising a plurality of edges and a plurality of nodes, each of the plurality of edges corresponding to a queue and each of the plurality of nodes corresponding to a computing function of the neural network system. A graph state is updated over a plurality of time steps according to the description of the neural network, the graph state being defined by the contents of each of the plurality of queues. Each of a plurality of assertions is tested at each of the plurality of time steps, each of the plurality of assertions being a function of a subset of the graph state. Invalidity of the neural network system is indicated for each violation of one of the plurality of assertions.

Systems and methods are disclosed for image classification of electro-optical images and synthetic aperture radar images using training techniques that can include appearance labeling and triplet mining to train a neural network system. The training data can include image pairs of electro-optical images and synthetic radar aperture images. The training data can include anchor, positive, and negative images. The neural network can be trained using triplet loss and cross-entropy loss. The trained neural network can be used for object classification such as automatic target recognition of aerial images.

A method for processing an input audio signal, comprising conditioning a first neural network system with a representation of the input audio signal to predict a bit-rate reduced representation of a processed input audio signal, the first neural network system being trained to generate a bit-rate reduced representation of a processed version of a given audio signal, wherein the bit-rate reduced representation has a format associated with a pre-defined audio encoding process, conditioning a second neural network system with the bit-rate reduced representation to predict an enhanced representation of the processed audio signal, the second neural network system being trained to generate an enhanced representation of a given a bit-rate reduced audio representation, wherein the bit-rate reduced representation has a format associated with the pre-defined audio encoding process, and transforming the enhanced representation of the processed audio signal into an output audio signal.

A method and system for correcting detector defects in an X-ray microscope system based on deep learning. Normal geometry projections and offset geometry projections are collected for a given detector, mappings between defective regions and healthy regions are created, and a machine learning system is trained using these projections. The trained neural network system is then used to correct the tomographic projection dataset, thereby improving the image quality of the resulting reconstructed tomographic image volume set.

A neural network system for predicting frequency coefficients of a media signal, the neural network system comprising a temporal prediction part comprising at least one neural network trained to predict a first set of output variables representing a particular frequency band of a current time frame given the coefficients of one or several preceding time frames, and a frequency prediction part comprising at least one neural network trained to predict a second set of output variables representing the particular frequency band given the coefficients of one or several frequency bands adjacent to the particular frequency band in the current time frame. Such a neural network system forms a predictor capable of capturing both the time dependency and the frequency dependency occurring in a time-frequency tile of a media signal.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a response to a query input using a selection-inference neural network.

A neural network circuit is described that includes a first sample-and-hold circuit, a reference voltage generation circuit, a first comparator circuit, and a first output circuit. The first sample-and-hold circuit generates a first analog voltage based on a first output current output by a first neural network computation array. The reference voltage generation circuit generates a reference voltage based on a first control signal. The first comparator circuit is connected to the first sample-and-hold circuit and the reference voltage generation circuit, and outputs a first level signal based on the first analog voltage and the reference voltage. The first output circuit samples the first level signal based on a second control signal, and outputs a first computation result that meets the first computation precision.

A neural network system includes a separable convolution subnetwork. The separable convolution subnetwork includes a plurality of separable convolutional neural network (SCNN) layers arranged in a stack manner in sequence. Each of the plurality of SCNN layers applies a first grouped convolution to an input to the SCNN layer. An input to the first grouped convolution includes a plurality of channels, and the first grouped convolution is a spatial convolution which divides channels of an input to the first grouped convolution into groups in a channel-wise manner, convolves the grouped channels, and couples the convolved channels to generate an output.

Systems and methods are provided for generating libraries for hardware realization of neural networks. The method includes obtaining a plurality of neural network topologies. Each neural network topology corresponds to a respective neural network. The method also includes transforming each neural network topology to a respective equivalent analog network of analog components. The method also includes generating a plurality of lithographic masks for fabricating a plurality of circuits. Each circuit implements a respective equivalent analog network of analog components.

Systems and methods for providing a neural network system for time series forecasting are described. A time series dataset that includes datapoints at a plurality of timestamps in an observed space is received. The neural network system is trained using the time series dataset. The training the neural network includes: generating, using an encoder of the neural network system, one or more estimated latent variables of a latent space for the time series dataset; generating, using an auxiliary predictor of the neural network system, a first latent-space prediction result based on the one or more estimated latent variables; transforming, using a decoder of the neural network system, the first latent-space prediction result to a first observed-space prediction result; and updating parameters of the neural network system based on a loss based on the first observed-space prediction result.

A neural network system is provided, implementing a generative model for autoregressively generating a distribution for a plurality of current filter-bank samples of an audio signal, wherein the current samples correspond to a current time slot, and each current sample corresponds to a channel of the filter-bank. The system includes a hierarchy of a plurality of neural network processing tiers ordered from a top to a bottom tier, each tier trained to generate conditioning information based on previous filter-bank samples and, for at least each tier but the top tier, also on the conditioning information from a tier higher up in the hierarchy, and an output stage trained to generate the probability distribution based on previous samples for one or more previous time slots and the conditioning information from the lowest processing tier.

Neural network systems and methods are provided. In one embodiment, a method of making a neural network device includes: forming a mesh layer on a substrate, the mesh layer including a matrix of randomly dispersed conductive nano-strands insulated from one another; forming an isolation trench extending into the mesh layer; forming a memristor device extending into the mesh layer, the memristor device including: an electrical conductor, and a layer of memristive material in electrical contact with individual nano-strands of a first set of conductive nano-strands in the mesh layer; forming an electrode extending into the mesh layer and spaced from the memristor device by the isolation trench, wherein the electrode is in electrical contact with individual conductive nano-strands of a second set of conductive nano-strands in the mesh layer; and forming a modulating device bridging the memristor device and the electrode.

This application provides a neural network system and a neural network calculation method, relating to the field of electronic technology, which can save chip area and power consumption. The neural network system includes a first memristor array, multiple current-to-voltage converters, and multiple resistive random access memories (RRAMs). The first memristor array includes multiple rows and columns of memristors for receiving first input data and performing multiplication and addition operations on the first input data according to configured first weights to obtain current. Each current-to-voltage converter is connected to the output terminal of at least one column of memristors in the first memristor array, for receiving the current of the corresponding column of memristors and converting the received current into voltage. Each RRAM is connected to at least one current-to-voltage converter, for receiving the voltage of the corresponding current-to-voltage converter, and obtaining one of the calculation results from the first calculation results based on the received voltage and the initial resistance state of the corresponding RRAM. The initial resistance state of each RRAM is a high resistance state.

Systems and methods are provided for configuring middleware to control a haptic device using a neural network. A system generates for display, based on at least one generic UI element, a virtual object within an XR environment. The XR application is configured to run on a local device, wherein the XR application causes display of the XR environment. The system configures middleware to run on the local device, wherein the middleware is configured to control at least one haptic device using at least one neural network. Based on avatar movement detected in the XR environment near the virtual object, the system causes the middleware to input control data into the at least one neural network. The at least one neural network outputs the control data for controlling the at least one haptic device. The system controls, by the middleware, the at least one haptic device based on the control data.

The present disclosure sets forth systems, apparatuses, and methods for dynamically generating and maintaining distributed neural networks with one or more edge systems. An example system comprises a first neural network having a first set of capabilities, an edge system in network communication with the first neural network, and a second neural network configured to determine a second set of capabilities of the edge system, generate, based on the first set of capabilities of the first neural network, based on the second set of capabilities of the edge system, and based on a schema, a third neural network that is a simplified version of the first neural network, and deploy the third neural network onto the edge system.

This invention discloses a leakage delay decomposition method for stabilizing finite-time complex-valued BAM neural networks. The specific design process is as follows: Based on the concepts of Lyapunov functionals and the upper right Dini derivative, some new sufficient conditions for the Fourier transform of complex-valued bidirectional associative memory neural networks with time delay are proposed. Using the decomposition technique of complex-valued bidirectional associative memory neural networks, the complex-valued nonlinear function is successfully decomposed into real and imaginary components, and a set of criteria is established. Simultaneously, under the two-layer structure of the complex-valued bidirectional associative memory neural network with time delay, a feedback controller is designed and implemented, providing important guarantees for the stability and stabilization of the network. This invention is of great significance for the control and stability of complex neural network systems.

The application provides a photonic neural network system based on a multi-task neural network, which comprises: an optical computing module, taking a photonic artificial intelligence chip as a core, modulating an optical signal, and completing multiplication, summation and nonlinear operation of high-precision and high-speed optical analog quantities; a multi-task neural network module, having a main branch neural network and multiple secondary branch neural networks, and capable of simultaneously processing multiple classification tasks and regression tasks; and an optical computing communication and control module based on FPGA, connected with the optical computing module and the multi-task neural network module, and used for realizing real-time and high-speed communication of the optical computing module and the multi-task neural network module. The system has the characteristics of high bandwidth and low energy consumption, utilizes high-dimension parallel computing to greatly reduce the time of original neural network serial operation, has the advantages of large network scale and fast parallel operation speed, and can improve recognition accuracy and shorten training time on the basis of a single task.

This invention discloses a neural network system and method for audio event detection. The system includes a feature extraction layer, a convolutional layer, a recurrent neural network, a feedforward network, and a self-attention module. The system processes the log-Mel spectrum features obtained from the extracted audio to obtain a three-dimensional feature map in the convolutional kernel space. It then calculates the frequency-adaptive attention weights for the three dimensions of the convolutional kernel space using these feature maps. Based on the three-dimensional frequency-adaptive attention weights and the base convolutional kernel, it performs a multiplication operation to determine the frequency-adaptive convolutional kernel. The frequency-adaptive convolutional kernel is used to perform multi-dimensional frequency dynamic convolution processing on the log-Mel spectrum features obtained from the extracted audio to obtain a first output feature. The sequence data of the first output feature is then processed to obtain a second output feature. Finally, strong and weak labels for the audio are obtained.

A waste management method includes setting an allowable methane amount in a bin and an allowable waste amount in the bin. The method includes measuring a methane amount in the bin, a waste amount in the bin, a temperature in the bin and a humidity in the bin, transmitting the methane amount, the temperature and the humidity to a first network and transmitting the waste amount, and the timestamp to a second network. The method includes generating a first time estimate with the first network and generating a second time estimate with the second network to determine whether the waste amount exceeds a predetermined allowable waste amount. The method includes generating a schedule and a route for a waste vehicle based on the first and second time estimates, a number of waste vehicles available, and methane emissions by the waste vehicles.

The present application relates to a neural network system, including at least: a multi-modal input neural network, configured to perform first encoding on multiple pieces of acquired environment sensing data corresponding to multiple input modalities to obtain multiple pieces of feature data for the multiple pieces of environment sensing data and perform first fusion on the multiple pieces of feature data to obtain fused multi-modal feature data; an encoder neural network, configured to at least perform second encoding on the multi-modal feature data to obtain multi-scale feature data, wherein the encoder neural network includes, for the multi-modal feature data, multiple stages respectively including at least two parallel branches for different resolutions; a decoder neural network, configured to decode the multi-scale feature data to obtain decoder output data; and a multi-modal output neural network, configured to obtain an environment sensing result when the decoder output data is used. The present application further relates to a training method, an environment sensing system and method, and a computer program product.

The invention discloses a multi-wavelength channel diffraction neural network system based on threshold screening and a processing method, and belongs to the technical field of artificial intelligence and optical computing. Comprising an encoding module used for encoding task information corresponding to different to-be-processed tasks to multiple light beams with different working wavelengths output by a light source module to form multiple task channel light fields; the optical diffraction module comprises a plurality of modulation layers; the optical diffraction module is used for receiving the task channel light fields and realizing diffraction modulation and threshold screening of the task channel light fields by changing the metasurface structures on different modulation layers; each task channel light field shares the same set of diffraction modulation parameters, namely parameters such as phase, mask generation and threshold; threshold screening: comparing the mask generation parameter with a threshold parameter, performing binarization selection on the phase parameter according to a comparison result, and screening out a target phase parameter; the output detection module detects the output light intensity. Task channels are expanded, and the system integration degree is improved.