Adaptive leakage value neuron information processing method and system

Abstract

The invention relates to a self-adaptive leakage value neuron information processing method and system. The method comprises the steps that the front-end pulse neuron output information is received; the current pulse neuron information including the self-adaptive membrane potential leakage information is read; the current pulse neuron output information is calculated based on the front-end pulse neuron output information and the current pulse neuron information; the self-adaptive membrane potential leakage information is updated based on the current pulse neuron output information; and the current pulse neuron output information is output. According to the self-adaptive leakage value neuron information processing system provided by the invention, the self-adaptive membrane potential leakage information participates in the calculation of the current pulse neuron output information; the current pulse neuron output information is calculated to update the self-adaptive membrane potential information to participate in the calculation of the next time step; great balance between the sensitivity and stability of a neural network is realized.

Description

technical field [0001] The invention relates to the technical field of artificial neural networks, in particular to a method and system for processing adaptive leakage value neuron information. Background technique [0002] The vast majority of today's artificial neural network research is still implemented in von Neumann computer software with high-performance GPGPU (General Purpose Graphic Processing Units). The hardware overhead, energy consumption and information processing of the entire process The speed is not optimistic. For this reason, the field of neuromorphic computing has developed rapidly in recent years, that is, using hardware circuits to directly construct neural networks to simulate the functions of the brain, trying to achieve a computing platform that is massively parallel, low-energy, and capable of supporting complex pattern learning. [0003] However, the traditional spiking neuron information processing method uses the historical membrane potential as...

AI Technical Summary

Problems solved by technology

[0004] Based on this, it is necessary to provide an adaptive leakage value neuron information processing method and system for how to solve the balance between sensitivity and stability of the neural network, wherein the method includes:

Images