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

Precise synaptic adjustment method for multi-pulse neural network supervised learning

A neural network and supervised learning technology, applied in the field of spiking neural networks, can solve problems such as difficult to guarantee synaptic weights, low learning efficiency, and difficult to control convergence speed

Active Publication Date: 2018-10-26
HANGZHOU DIANZI UNIV
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention aims at the problem that the membrane voltage threshold is simply set as a constant or fixed linear model in the existing SNN supervised learning algorithm, and the synaptic weight value generated by using the W-H rule is difficult to guarantee the optimal solution and the convergence speed is difficult to control. In the multi-pulse neural network learning algorithm, a precise synaptic adjustment method combining LIF and SRM neurons is proposed to solve the problems of low learning efficiency and uncontrollable convergence speed

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
  • Precise synaptic adjustment method for multi-pulse neural network supervised learning
  • Precise synaptic adjustment method for multi-pulse neural network supervised learning
  • Precise synaptic adjustment method for multi-pulse neural network supervised learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] Below in conjunction with accompanying drawing, the present invention is further described:

[0057] Step 1: Use LIF neurons to simulate membrane voltage and synaptic current

[0058] like figure 1 As shown, in the LIF neuron circuit, when the current I continues to increase, the voltage across the capacitor C will break through the threshold V th , at this time, a pulse signal will be excited and transmitted to the next layer of neurons. The formula for the total current in the circuit is:

[0059]

[0060] Set the time as a constant T, and let T=RC, then the above formula can be transformed into:

[0061]

[0062] It can be seen that this circuit is a parallel circuit, and the voltage V(t) on both sides of the capacitor C is exactly the membrane voltage. When the voltage is at t=t f reaches the threshold when V th , a pulse excitation will be generated; after that, the voltage will be quickly reset to the initial value, and a new round of accumulation will...

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 precise synaptic adjustment method for multi-pulse neural network supervised learning. The invention combines LIF and SRM neuron models to propose a threshold dynamic self-adaptive precise synaptic adjustment rule. The main steps are as follows: using LIF neuron to simulate and calculate membrane voltage and synaptic current; using a W-H rule to calculate synaptic weightadjustment; calculating dynamic threshold of membrane voltage by fusing the memory of postsynaptic neurons and SRM neurons; implementing input-output multi-pulse mapping. The invention realizes precise adjustment of synaptic weights by combining two neuron models, and effectively releases the problem that the weights derived from the W-H rule are difficult to guarantee the optimal solution and thelearning convergence rate is difficult to control, which effectively improves the learning efficiency of SNN.

Description

technical field [0001] The invention relates to the technical field of pulse neural networks, in particular to an accurate synaptic adjustment method for multi-pulse neural network supervised learning. Background technique [0002] Spiking Neural Networks (SNN) is known as the "third-generation neural network", which can better imitate the connection and communication between biological neurons than traditional artificial neural networks, and is an effective tool for complex spatiotemporal information processing. However, due to the discontinuous and nonlinear mechanism of SNN's internal pulse distribution, it is very difficult to construct an efficient SNN supervised learning algorithm. Traditional artificial neural network supervised learning algorithms such as error backpropagation (BackPropagation, BP) algorithm can no longer be used directly. Therefore, the focus of the SNN supervised learning algorithm is how to construct appropriate learning rules for synaptic weights...

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): G06F17/50G06N3/08
CPCG06N3/08G06F30/20
Inventor 徐小良卢文思金昕
Owner HANGZHOU DIANZI UNIV
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