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

Adaptive and classification method based on brain-like pulse neural network and computing device

A technology of spiking neural network and classification method, applied in the field of self-adaptive and classification methods and computing devices based on brain-like spiking neural network, to achieve high classification accuracy and solve the problem of spiking neuron threshold

Pending Publication Date: 2022-08-09
AUTOMOBILE RES INST OF TSINGHUA UNIV IN SUZHOU XIANGCHENG +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a brain-like impulse neural network-based adaptive and classification method and computing device that solves the problem of training SNN threshold parameter settings

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
  • Adaptive and classification method based on brain-like pulse neural network and computing device
  • Adaptive and classification method based on brain-like pulse neural network and computing device
  • Adaptive and classification method based on brain-like pulse neural network and computing device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043]In order for those skilled in the art to better understand the solutions of the present invention, and to more clearly understand the purpose, technical solutions and advantages of the present invention, the technical solutions in the embodiments of the present invention will be clarified below in conjunction with specific embodiments and with reference to the accompanying drawings. fully described. It should be noted that the implementations not shown or described in the accompanying drawings are the forms known to those of ordinary skill in the art. Additionally, although examples of parameters including specific values ​​may be provided herein, it should be understood that the parameters need not be exactly equal to the corresponding values, but may be approximated within acceptable error tolerances or design constraints. Obviously, the described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present inve...

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 brain-like spiking neural network-based adaptive and classification method and a computing device, the spiking neural network is configured to input spiking neurons for activation, and the activation process comprises discharging; the self-adaptive threshold value method comprises the following steps: setting a pulse emission threshold value of the pulse neuron as a median of a current tensor; the spiking neuron is configured to discharge according to the following discharge equation: S (t) = sign (U (t)-Uth), when U (t)-Uthgt; when 0, S (t) = 1; when U (t)-Uth is other, S (t) is equal to 0; wherein S (t) is a pulse emitted by a pulse neuron, sign () is a sign function, U (t) is a membrane potential at a t moment, and Uth is a pulse emission threshold value. The technical scheme provided by the invention can solve the problem of training SNN threshold parameter setting, and not only solves the problem of spiking neuron threshold, but also keeps higher classification precision of the SNN algorithm through the method of configuring the adaptive threshold for the SNN algorithm.

Description

technical field [0001] The invention relates to the field of impulse neural networks, in particular to an adaptive and classification method and a computing device based on a brain-like impulse neural network. Background technique [0002] Spiking Neural Network (SNN), as the third generation of artificial neural network, mainly uses spiking neurons to receive and transmit information. Unlike Deep Neural Network (DNN), which only uses the spatial domain information of the network, SNN encodes the input information of the network into spatial domain signals, and maintains the temporal domain relationship during the signal transmission process. This way of processing information is more efficient. Close to the real biological nervous system, it can better reflect the essence of intelligence. SNNs have received more and more attention from researchers due to their better biological interpretability, low power consumption, fast speed, and high accuracy to train SNNs. [0003] ...

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): G06N3/04G06N3/08G06K9/62
CPCG06N3/049G06N3/084G06N3/048G06F18/2415Y02D10/00
Inventor 孙国梁郑四发
Owner AUTOMOBILE RES INST OF TSINGHUA UNIV IN SUZHOU XIANGCHENG
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com