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

Spiking neuron reinforcing circuit and reinforcing method

A neuron and neuron computing technology, applied in the field of pulsed neural networks, can solve problems such as outputting wrong pulse signals, abnormal neuron discharge behavior, and wrong output results of brain-like neuromorphic computing chips, so as to improve adaptability and reliability sexual effect

Pending Publication Date: 2022-05-24
BEIJING MXTRONICS CORP +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Spike neurons are very susceptible to single-event effects in space applications. If the neuron model parameters are caused by single-event flips or single-event transients, single or multiple dislocations will result in abnormal neuron discharge behavior and output errors. If the pulse signal is serious, it will cause the output result of the brain-like neuromorphic computing chip to be wrong.

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
  • Spiking neuron reinforcing circuit and reinforcing method
  • Spiking neuron reinforcing circuit and reinforcing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] An impulse neuron reinforcement circuit and reinforcement method, comprising configuration information memory (or register group), model parameter memory (or register group), ECC encoding module, ECC decoding module, configurable neuron computing unit, shadow memory (or register) group), arbitration correction control logic module;

[0051]The configuration information memory (or register group) stores the configuration information of various neuron models, and the configurable neuron computing unit can generate the required spiking neurons according to the configuration information, such as LIF neurons or Izhikevich neurons or Hodgkin-Huxley neurons Neurons;

[0052] The model parameter memory (or register group) stores the parameter information corresponding to various neuron models, and the configurable neuron computing unit can realize the corresponding excited or inhibited neuron discharge pulse signals according to the model parameter information, such as the stor...

Embodiment 2

[0070] A spiking neuron reinforcement circuit and reinforcement method can specifically include a configuration information memory, a model parameter memory, an ECC encoding module, an ECC decoding module, a configurable neuron computing unit, a shadow memory, and an arbitration correction control logic module.

[0071] The output of the ECC encoding module is connected to the configuration information memory and the model parameter memory.

[0072] The outputs of the configuration information memory and the model parameter memory are connected to the ECC decoding module.

[0073] The outputs of the ECC decoding module and the shadow memory are connected to the arbitration correction control logic module.

[0074] The output of the arbitration correction control logic module is connected to the configurable neuron computing unit and the ECC encoding module.

[0075] In the embodiment of the present invention, for the consideration of low power consumption and resource saving,...

Embodiment 3

[0094] An impulse neuron reinforcement circuit, comprising a first register group, a second register group, a third register group, an encoding module, a decoding module, a logic module, and a configurable impulse neuron computing unit;

[0095] The encoding module is used for encoding the first data and or the second data input by the external or logic module;

[0096] The first register group is used to store the encoded first data;

[0097] The second register group is used to store the encoded second data;

[0098] The third register group is used to directly store the first data and or the second data;

[0099] The decoding module is used to perform error correction and detection decoding on the encoded first data and or the second data, and record the decoding result; the encoding mode of the encoding module corresponds to the decoding mode of the decoding module;

[0100] The logic module selects the decoded first data and / or second data to output to the configurable ...

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 relates to a spiking neuron reinforcing circuit and a spiking neuron reinforcing method, which solve the defect in the prior art that the spiking neuron is easily subjected to calculation errors due to the influence of a single event effect, and effectively improve the space environment adaptability of the spiking neuron. According to the method, spiking neurons and neuron discharge pulse signals required by the spiking neural network can be realized through configuration information and model parameters; furthermore, according to the method, error detection and fault tolerance are carried out on configuration information and model parameters through an ECC coding and decoding module; further, according to the method, backup fault tolerance is carried out on configuration information and model parameters through a shadow memory (or a register block).

Description

technical field [0001] The invention relates to an impulse neuron reinforcement circuit and a reinforcement method, and relates to the technical field of impulse neural networks. Background technique [0002] As a third-generation neural network, spiking neural network is widely used in the field of brain-like neuromorphic computing due to its bionic neural dynamics and event-driven advantages. The spiking neuron is the basic computing unit of the spiking neural network, which simulates the working mode of the biological neuron. information transfer between. The spiking neuron outputs the spiking signal of excitatory or inhibited neuron firing through the calculation of neuron model parameters. Commonly used spiking neuron models include the LIF model proposed by Lapicque in 1907, the Izhikevich model proposed by E.M.Izhikevich in 2003, and the Hodgkin-Huxley model proposed by Hodgkin and Huxley in 1952. The Izhikevich model can simulate the 20 most prominent excitations o...

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): G06N3/063
CPCG06N3/063
Inventor 覃辉陈雷王亮宋立国陈淼郑宏超李同德诸磊赵元富
Owner BEIJING MXTRONICS CORP
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