A novel spiking neural network of receptive field encoding with groups of neurons decision

作     者：Yong-qiang MA Zi-ru WANG Si-yu YU Ba-dong CHEN Nan-ning ZHENG Peng-ju REN 

作者机构：Institute of Artificial Intelligence and RoboticsXi'an Jiaotong University 

出 版 物：《Frontiers of Information Technology & Electronic Engineering》 (信息与电子工程前沿（英文版）)

年 卷 期：2018年第19卷第1期

页      面：139-150页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China(Nos.61773312,61773307,and L1522023) the China Postdoctoral Science Foundation(No.2016M590949) the National Basic Research Program(973)of China(No.2015CB351703) 

主　　题：Tempotron Receptive field Difference of Gaussian(DoG) Flip invariance Rotation invariance 

摘      要：Human information processing depends mainly on billions of neurons which constitute a complex neural network,and the information is transmitted in the form of neural *** this paper,we propose a spiking neural network(SNN),named MD-SNN,with three key features:(1) using receptive field to encode spike trains from images;(2) randomly selecting partial spikes as inputs for each neuron to approach the absolute refractory period of the neuron;(3) using groups of neurons to make *** test MD-SNN on the MNIST data set of handwritten digits,and results demonstrate that:(1) Different sizes of receptive fields influence classification results significantly.(2) Considering the neuronal refractory period in the SNN model,increasing the number of neurons in the learning layer could greatly reduce the training time,effectively reduce the probability of over-fitting,and improve the accuracy by 8.77%.(3) Compared with other SNN methods,MD-SNN achieves a better classification;compared with the convolution neural network,MD-SNN maintains flip and rotation invariance(the accuracy can remain at 90.44% on the test set),and it is more suitable for small sample learning(the accuracy can reach 80.15%for 1000 training samples,which is 7.8 times that of CNN).