|
Frontiers of Information Technology & Electronic Engineering
ISSN 2095-9184 (print), ISSN 2095-9230 (online)
2018 Vol.19 No.1 P.139-150
A novel spiking neural network of receptive field encoding with groups of neurons decision
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).
Key words: Tempotron, Receptive field, Difference of Gaussian (DoG), Flip invariance, Rotation invariance
关键词组:
References:
Open peer comments: Debate/Discuss/Question/Opinion
<1>
DOI:
10.1631/FITEE.1700714
CLC number:
TP183
Download Full Text:
Downloaded:
2430
Download summary:
<Click Here>Downloaded:
1743Clicked:
6842
Cited:
0
On-line Access:
2018-03-10
Received:
2017-10-31
Revision Accepted:
2018-01-22
Crosschecked:
2018-01-25