Method and system for converting spiking neural network information into artificial neural network information

Abstract

The invention relates to a method for converting pulse neural network information into artificial neural network information. The method includes the steps that a conversion time step is obtained; within the duration of the conversion time step, pulse neuron input information input by an anterior pulse neuron is received, and the pulse neuron input information includes pulse spike information; according to the pulse spike information input by the anterior pulse neuron, through a preset pulse conversion algorithm, artificial neuron conversion information is obtained; the artificial neuron conversion information is output. According to the method for converting the pulse neural network information into the artificial neural network information, the pulse neural network information is converted into the artificial neural network information on the basis of a time-step-based conversion mode, the compatible capability of neural networks on the pulse neural network information and the artificial neural network information is improved.

Description

technical field [0001] The invention relates to the technical field of neural networks, and relates to a method and system for converting neural network information, in particular to a method and system for converting pulse neural network information into artificial neural network information. Background technique [0002] Most of today's artificial neural network research is still implemented in von Neumann computer software and high-performance GPGPU (General Purpose Graphic Processing Units) platform. The hardware overhead, energy consumption and information of the whole process The processing 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, in the ...

AI Technical Summary

Problems solved by technology

[0003] However, in traditional neuromorphic systems, there are mainly two forms of neural networks, one is spiking neural network and the other is artificial neural network. The two have different expressions for the same input information, resulting in artificial neural network and spiking Neural networks are not compatible due to the different information they process

Images