Lynxi Technologies Co., Ltd.

Tsinghua University

Zhenzhi Wu

Yaolong Zhu

Wei He

Lei Deng

Luping Shi

Jing Pei

Guoqi Li

Luojun Jin

Qikun Zhang

Qune Kong

Xin Ma

Guanrui Wang

A behavior recognition method and system, including: dividing video data into a plurality of video clips, performing frame extraction processing on each video clip to obtain frame images, and performing optical flow extraction on the frame images to obtain optical flow images; performing feature extraction on the frame images and the optical flow images to obtain feature maps of the frame images and the optical flow images; performing spatio-temporal convolution processing on the feature maps of the frame images and the optical flow images, and determining a spatial prediction result and a temporal prediction result; fusing the spatial prediction results of all the video clips to obtain a spatial fusion result, and fusing the temporal prediction results of all the video clips to obtain a temporal fusion result; and performing two-stream fusion on the spatial fusion result and the temporal fusion result to obtain a behavior recognition result.

Behavior recognition method and system, electronic device and computer-readable storage medium

The present disclosure relates to a synaptic weight training method, a target identification method, an electronic device and a storage medium. The synaptic weight training method includes: inputting spike signals corresponding to training samples into a spiking neural network to be trained; learning a target synaptic weight in the spiking neural network with a back propagation rule to obtain a first branch weight; and learning the target synaptic weight with a synaptic plasticity rule to obtain a second branch weight; and updating the target synaptic weight according to the first branch weight and the second branch weight.

Synaptic weight training method, target identification method, electronic device and medium

Provided is a method for training spiking neuron network, including: inputting a spiking signal corresponding to a training sample into a spiking neuron network to be trained; and training the spiking neuron network based on a back propagation rule, wherein a forward propagation stage of training includes: adjusting a spiking firing threshold corresponding to a target layer in the spiking neuron network according to confidence corresponding to the target layer. Also provided are a method for processing data based on a spiking neuron network, an electronic device, and a non-transitory computer-readable medium.

Methods, electronic devices, and computer-readable media for training, and processing data through, a spiking neuron network

A computing core circuit, including: an encoding module, a route sending module, and a control module, wherein the control module is configured to control the encoding module to perform encoding processing on a pulse sequence determined by pulses of at least one neuron in a current computing core to be transmitted, so as to obtain an encoded pulse sequence, and control the route sending module to determine a corresponding route packet according to the encoded pulse sequence, so as to send the route packet. The present disclosure further provides a data processing method, a chip, a board, an electronic device, and a computer-readable storage medium.

Spiking neural network-based data processing method, computing core circuit, and chip

The present disclosure provides a method for converting numerical values into spikes. The method includes: generating an initial spike sequence according to input numerical values, where the initial spike sequence includes at least one data string, each of which is independently selected from one of a consecutive spike train or a consecutive non-spike train, the number of spikes in all of the at least one data string is equal to an expected value of the number of spikes in a target spike sequence to be generated, and the target spike sequence to be generated is a spike sequence of a spiking neural network within a time period; and randomly selecting and modifying data from the initial spike sequence, so as to form the target spike sequence. The present disclosure further provides an apparatus for converting numerical values into spikes, an electronic device, and a computer-readable storage medium.

Method and apparatus for converting numerical values into spikes, electronic device and storage medium

A video retrieval method and apparatus, a device and a storage medium are provided. The method comprises the following steps: acquiring a comparison video clip from a video library according to the duration of a to-be-tested video (S); determining the similarity between the to-be-tested video and the comparison video clip by a target spatio-temporal neural network, a spatio-temporal convolutional layer of the target spatio-temporal neural network being configured to be capable of performing two-dimensional convolution and temporal dimension information processing, respectively (S); and traversing the video library, and outputting a retrieval result according to the similarity (S).

Video retrieval method and apparatus, device and storage medium

The disclosure relates to a self-adaptive leakage value neuron information processing method and system. The method includes: receiving front end pulse neuron output information; reading current pulse neuron information, wherein the current pulse neuron information includes self-adaptive membrane potential leakage information; calculating current pulse neuron output information according to the front end pulse neuron output information and the current pulse neuron information; updating the self-adaptive membrane potential leakage information according to the current pulse neuron output information; outputting the current pulse neuron output information. The self-adaptive leakage value neuron information processing system utilizes self-adaptive membrane potential leakage information to participate in calculation of current pulse neuron output information, and utilizes the calculated current pulse neuron output information to update the self-adaptive membrane potential information to participate in calculation of a next time step, and a good balance between sensitivity and stability of a neural network is achieved.

Self-adaptive threshold neuron information processing method, self-adaptive leakage value neuron information processing method, system computer device and readable storage medium

There are provided a neural network weight discretizing method, system and device, and a computer readable storage medium. The method includes acquiring a weight value range and a number of discrete weight states, the weight value range referring to a range of discrete weight values consisting of a maximum weight value of a current time step and a minimum weight value of the current time step, and the number of discrete weight states referring to the quantity of discrete weight states. The method also includes acquiring a weight state of a previous time step and a weight increment of the current time step and acquiring a state transfer direction by using a directional function according to the weight increment of the current time step. The method also includes acquiring a weight state of the current time step according to the weight state of the previous time step, the weight increment of the current time step, the state transfer direction, the weight value range and the number of discrete weight states. The method ensures that the weight value is always constrained in the same discrete-state space without the need for storing an additional virtual continuous-state implicit weight. On the premise that the computation performance of the neural network is ensured, the consumption of storage space is greatly reduced, and the computation complexity is reduced.

Neural network weight discretizing method, system, device, and readable storage medium

The present disclosure provides a brain-like computing chip and a computing device. The brain-like computing chip includes is a many-core system composed of one or more functional cores, and data transmission is performed between the functional cores by means of a network-on-chip. The functional core includes at least one neuron processor configured to compute various neuron models, and at least one coprocessor coupled to the neuron processor and configured to perform an integral operation and/or a multiply-add-type operation; and the neuron processor is capable of calling the coprocessor to perform the multiply-add-type operation.

Growing community of inventors

Beijing, China

Zhenzhi Wu