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

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...

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

Images