Search | Engineering

Subscribe Submit

Home Journals Focus Achievement Fronts About Us 中文版

Resource Type

Journal Article 1

Year

2018 1

Keywords

Difference of Gaussian (DoG) 1

Flip invariance 1

Receptive field 1

Rotation invariance 1

Tempotron 1

Search scope:

排序： Display mode:

Anovel spiking neural network of receptive field encoding with groups of neurons decision Article

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

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 1, Pages 139-150 doi: 10.1631/FITEE.1700714

Abstract: 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 spikes. In 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 decisions. We 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).

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