Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Simulation and training method of pulse neural network with pulse moment offset

A technology of pulse neural network and time offset, which is applied in the field of neural network technology and brain-inspired computing, can solve the problems of SNN simulation and training errors, error expansion, and reduced calculation efficiency, so as to improve the accuracy of simulation calculations and eliminate inherent errors , the effect of improving simulation efficiency

Inactive Publication Date: 2022-01-14
ZHEJIANG LAB +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This clock-driven calculation method causes neurons to only calculate the pulse emission at the time step, and there is a certain error between the pulse time based on the time step and the real pulse time.
Through pulse transmission, the error existing at the pulse time will be further enlarged, which seriously affects the simulation calculation accuracy of SNN
In order to ensure the calculation accuracy, a smaller time step is usually required, but a smaller time step increases the calculation amount of simulation and training, and reduces the calculation efficiency
Secondly, because SNN has non-differentiable mutations in the process of pulse generation, SNN cannot directly use the standard gradient error backpropagation method for learning
Existing SNN algorithms usually use the method of substituting gradients for pulse transmission to reverse the error through the state quantity at each time step, but the existing substituting gradient methods cannot approximate the gradient changes in the two directions of pulse emission probability and pulse time movement, so the SNN network There is a large deviation in the gradient calculation of
In summary, the existing SNN clock-driven calculation method causes large errors in SNN simulation and training, which limits the application of SNN technology in complex artificial intelligence tasks

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Simulation and training method of pulse neural network with pulse moment offset
  • Simulation and training method of pulse neural network with pulse moment offset
  • Simulation and training method of pulse neural network with pulse moment offset

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The spiking neuron model and its network simulation training method provided by the present invention can be applied to various brain-inspired intelligent tasks such as image and audio information recognition. The embodiment of the present invention will be described in detail below by taking speech recognition as an example in conjunction with the accompanying drawings. The examples and figures are not intended to limit the scope of the invention. It should be noted that, in order to highlight the main content of the present invention in the following description, detailed descriptions of known functions and designs of existing methods in the implementation manners will be omitted.

[0075] Such as figure 1 As shown, the simulation and training method of the spike neural network with pulse time offset is applied to the speech recognition task, including the following steps:

[0076] S1. Obtain training data, select pulse codec and loss function, and construct a pulse...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a simulation and training method of a pulse neural network with pulse moment offset, which comprises the following steps of: discretizing to update a neuron state quantity step by step, estimating whether pulse distribution is generated in a time step range and the moment offset thereof, calculating pulse input at the next moment according to synaptic connection and repeating the process to complete network simulation; and according to simulation result delay neuron state quantity, pulse emission quantity and time offset back propagation gradient error, updating network parameters. Errors in time step-by-step simulation calculation of the pulse neural network are reduced, and the simulation efficiency is improved under the same precision condition. And meanwhile, the pulse error is transmitted through two dimensions of the pulse emission amount and the time offset in the error back propagation algorithm, so that the training efficiency is improved.

Description

technical field [0001] The invention relates to the fields of neural network technology and brain-inspired computing technology, in particular to a simulation and training method of a pulse neural network with a pulse time offset. Background technique [0002] Spiking neural network (SNN) is a neural network technology that more accurately simulates the calculation and communication mechanism of the biological nervous system and is closer to the information processing method of the human brain. The dynamic mechanism of pulse generation of spiking neurons makes SNN have inherent ability to process historical information. Compared with traditional artificial neural networks, it has unique advantages in processing spatio-temporal information. At the same time, the way of transmitting information by pulses saves computing resources. Therefore, the spiking neural network is an important technical tool in the field of brain-inspired intelligence. [0003] However, the continuous ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/049G06N3/084
Inventor 洪朝飞唐华锦袁孟雯王笑张梦骁陆宇婧黄恒赵文一燕锐潘纲
Owner ZHEJIANG LAB
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products