124 results about "Neural network system" patented technology

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.

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.

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.

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 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 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.

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.

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.

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.

The invention discloses an optical switch device and a complex-valued optical neural network system, and belongs to the technical field of optical computing. The optical switch device is a two-input two-output device and comprises first to sixth waveguides, and first and second multimode interference couplers. Phase shifters are attached to the third waveguide and the fifth waveguide and / or the fourth waveguide and the sixth waveguide to form a group of configuration units which are used for loading real part and imaginary part data of a complex number. The phase shifter comprises a nonvolatile phase change material layer and a heating layer which are sequentially arranged from bottom to top, is used for realizing the function of the phase shifter, greatly reduces the static power consumption, improves the energy efficiency, is suitable for realizing the complex value optical neural network, and is also beneficial to large-scale integration. The complex-valued optical neural network system constructed based on the optical switch integrates input, calculation, reference and coherent detection modules, can synchronously complete amplitude and phase detection of optical signals, effectively supports complex-valued optical calculation, and has the advantages of low power consumption and high integration level.

An apparatus (e.g., an ear-worn device such as a hearing aid) may include a neural network circuit and a control circuit. The neural network circuit may be configured to implement a neural network system including at least a first neural network and a second neural network operating in parallel. The control circuit may be configured to control the neural network system to receive a first input signal, process the first input signal using a first neural network to produce a first output, and process the first input signal using a second neural network to produce a second output, combine the first output and the second output, and output the combined output. The one or more states of the first neural network are reset, and the one or more states of the second neural network are reset at a different time than the one or more states of the first neural network are reset.

A spiking neural network (SNN) system is disclosed having spiking neurons associated with clause values associated with a satisfiability (SAT) problem. Each spiking neuron generates a voltage spike when on input voltage applied to each spiking neuron is increased above a spiking voltage threshold. The input voltage that is increased above the spiking voltage threshold is indicative that the corresponding clause value is satisfied. A controller applies the clause grid that includes clause values to a literal grid that includes literal values. The controller generates the input voltage that is applied to each spiking neuron based on each corresponding clause value associated with each spiking neuron that is applied to the literal values. The controller determines that each clause value is satisfied when the corresponding spiking neuron generates the voltage spike and that each clause value is unsatisfied when the corresponding spiking neuron fails to generate the voltage spike.

The application discloses a finite time synchronization and quantization control method of a memristor neural network, and comprises the following steps: step 1, constructing a memristor neural network system model; step 2, constructing a controller for the memristor neural network system model in step 1; step 3, constructing definitions and lemmas required for time synchronization and quantization control of the memristor neural network; and step 4, combining steps 1 to 3 to perform time synchronization and quantization control on the memristor neural network. The application proposes a new control theory and analysis method for finite time synchronization and quantization control of the memristor neural network based on theories such as comprehensive differential equations, neural networks, quantization control and finite time stability, and provides a new idea and approach for synchronization and control research of the memristor neural network.

Systems, methods, and devices, for melanoma pathology using one or more neural networks (NNs). The techniques described herein may include receiving molecular data corresponding to a patient biopsy sample; molecular data; encoding molecular output data according to a preselected encoding scheme; receiving image data corresponding to the patient biopsy sample; applying the image data to an image analysis NN; concatenate the encoded molecular data to the image data at an intermediate layer of the image analysis NN; and producing, based on the encoded molecular information and the image information concatenated at the intermediate layer, a prognosis output from the image analysis NN. Many other features and examples are described herein.

The invention relates to an articulated robotic arm device with a neural-network system for movement of a robotic arm, the neural-network system being capable of learning online and in real time the forces for moving its joints towards a target position by simulation of virtual springs implementing impedance control, wherein learning the rest elongations of the virtual springs for a selected state defines the equilibrium position of the arm corresponding to a zero resultant of the forces applied to the arm, thereby giving the arm elasticity properties as a function of the stiffness selected for the springs, at equilibrium, wherein the neural network learns these elongations for each transition from one target position to another target position in the joint space, making it possible to control movement of the arm in order to learn a sequence of movements and define the behavior of the arm for a given task, each joint of the arm having a target position.

Systems or techniques that facilitate a dual quantum recurrent neural network with an attention mechanism for time series prediction are provided. In various embodiments, a system can receive a time series. In various cases, the system can further generate a prediction of the time series via a dual quantum recurrent neural network (QRNN), the dual QRNN comprising: a primary QRNN; and a controller QRNN that determines, via an attention mechanism, relevant past cell states of the primary QRNN, and wherein the primary QRNN generates the prediction of the time series based on the relevant past cell states.

A coupling strength update device is configured to comprise: a coupling strength management unit (3) that manages the coupling strength between a first neuron, which is a certain neuron among a plurality of neurons included in a spiking neural network, and a second neuron, which is a neuron that acquires a spike signal outputted from the first neuron upon firing of the first neuron; an elapsed time management unit (1) that manages the elapsed time since the spike signal was outputted from the first neuron; and a firing rate management unit (2) that manages the firing rate, which is a rate at which the first neuron fires. In addition, when the second neuron fires, the coupling strength management unit (3) of the coupling strength update device updates the coupling strength between the first neuron and the second neuron on the basis of the elapsed time managed by the elapsed time management unit (1) and the firing rate managed by the firing rate management unit (2).

The invention provides a neural network system, method and device for multiple rounds of conversations and a storage medium. The neural network system comprises one or more neural network subsystems; the at least one subsystem comprises a first neural network layer, a hybrid expert network layer and a second neural network layer; the hybrid expert network layer comprises N routing layers, M expert neural network sets and an output layer; the ith routing layer selects at least one expert neural network from j expert neural network sets according to round parameters corresponding to the ith round of dialogue and the output of the first neural network layer, the output of the first neural network layer serves as the input of the selected expert neural network, i is larger than 0 and smaller than or equal to N, and j is larger than 0 and smaller than or equal to M; the expert neural network processes the output of the first neural network layer to obtain a processing result; and the output layer combines the processing results output by the expert neural network selected by the ith routing layer, and takes the combined result as the input of the second neural network layer.

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.

The application provides a temperature measurement method and device, computer equipment and a storage medium, and belongs to the field of temperature measurement. The method comprises the following steps: acquiring sample data; constructing a plurality of luminance value and temperature relationship formulas according to a plurality of spectral response logarithm ratios and a two-color temperature measurement formula; constructing a unit structure of luminance value mapping to predicted temperature; determining physical constraints according to the plurality of luminance value and temperature relationship formulas; constructing a neural network model of luminance value mapping to predicted temperature according to the unit structure and the physical constraints; training the neural network model through the sample data, determining unknown parameters, and then obtaining a temperature prediction model; acquiring a temperature field image of a target object; inputting the temperature field image of the target object into the temperature prediction model to obtain the temperature of the target object. The neural network system constructed through physical constraints reduces the dependence of the normalization process on the true temperature value, and improves the convenience of temperature measurement.

A neural network system is provided that includes at least one layer that applies a 1x1 convolution to a dense activation matrix using a kernel defined by a sparse weight matrix. The layer is implemented by a processor by accessing a sparsity dataset that indicates the locations of empty weights in the weight matrix. The processor selects feature values corresponding to other weights from a memory unit configured to store the activation matrix, and then uses these extracted feature values to compute the convolution values.