Supervised Learning Algorithm Based on Spike Train Inner Product for Deep Spiking Neural Networks

By mimicking the hierarchical structure of human brain, deep spiking neural networks (DSNNs) can extract features from a lower level to a higher level gradually, and improve the performance for the processing of spatio-temporal information. Due to the complex hierarchical structure and implicit nonl...

Full description

Saved in:
Bibliographic Details
Published in:Brain sciences 2023-01, Vol.13 (2), p.168
Main Authors: Lin, Xianghong, Zhang, Zhen, Zheng, Donghao
Format: Article
Language:English
Subjects:
Algorithms
Approximation
Back propagation
Brain research
Computational linguistics
Data mining
Deep learning
Feedback
feedback alignment mechanism
Firing pattern
Information processing
Information storage
Language processing
Learning
Machine learning
Natural language interfaces
Neural networks
Neurons
Neurophysiology
Pattern recognition
Signal processing
spike train inner product
spiking neural networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:By mimicking the hierarchical structure of human brain, deep spiking neural networks (DSNNs) can extract features from a lower level to a higher level gradually, and improve the performance for the processing of spatio-temporal information. Due to the complex hierarchical structure and implicit nonlinear mechanism, the formulation of spike train level supervised learning methods for DSNNs remains an important problem in this research area. Based on the definition of kernel function and spike trains inner product (STIP) as well as the idea of error backpropagation (BP), this paper firstly proposes a deep supervised learning algorithm for DSNNs named BP-STIP. Furthermore, in order to alleviate the intrinsic weight transport problem of the BP mechanism, feedback alignment (FA) and broadcast alignment (BA) mechanisms are utilized to optimize the error feedback mode of BP-STIP, and two deep supervised learning algorithms named FA-STIP and BA-STIP are also proposed. In the experiments, the effectiveness of the proposed three DSNN algorithms is verified on the MNIST digital image benchmark dataset, and the influence of different kernel functions on the learning performance of DSNNs with different network scales is analyzed. Experimental results show that the FA-STIP and BP-STIP algorithms can achieve 94.73% and 95.65% classification accuracy, which apparently possess better learning performance and stability compared with the benchmark algorithm BP-STIP.
ISSN:2076-3425
2076-3425
DOI:10.3390/brainsci13020168