Image recognition system and method based on spiking neural network

Abstract

The invention discloses an image recognition system and method based on a pulse neural network. The system comprises an upper computer, an off-chip memory, a master control module, an input coding module, an LIF neuron module, a pulse time information processing module, a TSTDP module and a full voting module. The method comprises the following steps: a training stage: training synaptic weights between an input layer and a hidden layer, between the hidden layers and between the hidden layer and an output layer of the spiking neural network; a benchmarking stage: training a synaptic weight between an output layer of the spiking neural network and a full voting classification layer; in the recognition stage, the output layer votes for the full-voting classification layer by adopting a full-voting mechanism, and image recognition is carried out. The invention provides a full voting output decoding mechanism capable of reducing information loss, and the problem of output decoding information loss of a pulse neural network caused by a traditional voting mechanism is effectively improved. The method can be widely applied to the technical field of artificial neural network and digital circuit design.

Description

technical field [0001] The invention relates to the technical field of artificial neural network and digital circuit design, in particular to an image recognition system and method based on a pulse neural network. Background technique [0002] In recent years, artificial intelligence has touched all aspects of people's lives, and has achieved good results in image recognition, speech recognition, target detection, etc., and has therefore attracted extensive attention from researchers. However, the traditional first- and second-generation artificial neural networks only simulate the structure of the biological brain in an abstract and simplified manner from the physical structure, which is not completely consistent with the biological mechanism of the brain to process information. The traditional artificial neural network is more inclined to improve the performance of the neural network from the perspective of computational science, and to improve the ability of the network t...

AI Technical Summary

Problems solved by technology

[0006] The realization of the bionic nature of the spiking neural network needs to involve a large number of complex differential and exponential operations, which is more suitable for research in the field of biological sciences, but in specific practical applications such as image recognition, it will add too much extra overhead to the hardware platform

Images