Cargando…

Spike-Based Approximate Backpropagation Algorithm of Brain-Inspired Deep SNN for Sonar Target Classification

With the development of neuromorphic computing, more and more attention has been paid to a brain-inspired spiking neural network (SNN) because of its ultralow energy consumption and high-performance spatiotemporal information processing. Due to the discontinuity of the spiking neuronal activation fu...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Yang, Tian, Meng, Liu, Ruijia, Cao, Kejing, Wang, Ruiyi, Wang, Yadi, Zhao, Wei, Zhou, Yi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9613403/
https://www.ncbi.nlm.nih.gov/pubmed/36313052
http://dx.doi.org/10.1155/2022/1633946
_version_ 1784819982059700224
author Liu, Yang
Tian, Meng
Liu, Ruijia
Cao, Kejing
Wang, Ruiyi
Wang, Yadi
Zhao, Wei
Zhou, Yi
author_facet Liu, Yang
Tian, Meng
Liu, Ruijia
Cao, Kejing
Wang, Ruiyi
Wang, Yadi
Zhao, Wei
Zhou, Yi
author_sort Liu, Yang
collection PubMed
description With the development of neuromorphic computing, more and more attention has been paid to a brain-inspired spiking neural network (SNN) because of its ultralow energy consumption and high-performance spatiotemporal information processing. Due to the discontinuity of the spiking neuronal activation function, it is still a difficult problem to train brain-inspired deep SNN directly, so SNN has not yet shown performance comparable to that of an artificial neural network. For this reason, the spike-based approximate backpropagation (SABP) algorithm and a general brain-inspired SNN framework are proposed in this paper. The combination of the two can be used for end-to-end direct training of brain-inspired deep SNN. Experiments show that compared with other spike-based methods of directly training SNN, the classification accuracy of this method is close to the best results on MNIST and CIFAR-10 datasets and achieves the best classification accuracy on sonar image target classification (SITC) of small sample datasets. Further analysis shows that compared with artificial neural networks, our brain-inspired SNN has great advantages in computational complexity and energy consumption in sonar target classification.
format Online
Article
Text
id pubmed-9613403
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-96134032022-10-28 Spike-Based Approximate Backpropagation Algorithm of Brain-Inspired Deep SNN for Sonar Target Classification Liu, Yang Tian, Meng Liu, Ruijia Cao, Kejing Wang, Ruiyi Wang, Yadi Zhao, Wei Zhou, Yi Comput Intell Neurosci Research Article With the development of neuromorphic computing, more and more attention has been paid to a brain-inspired spiking neural network (SNN) because of its ultralow energy consumption and high-performance spatiotemporal information processing. Due to the discontinuity of the spiking neuronal activation function, it is still a difficult problem to train brain-inspired deep SNN directly, so SNN has not yet shown performance comparable to that of an artificial neural network. For this reason, the spike-based approximate backpropagation (SABP) algorithm and a general brain-inspired SNN framework are proposed in this paper. The combination of the two can be used for end-to-end direct training of brain-inspired deep SNN. Experiments show that compared with other spike-based methods of directly training SNN, the classification accuracy of this method is close to the best results on MNIST and CIFAR-10 datasets and achieves the best classification accuracy on sonar image target classification (SITC) of small sample datasets. Further analysis shows that compared with artificial neural networks, our brain-inspired SNN has great advantages in computational complexity and energy consumption in sonar target classification. Hindawi 2022-10-20 /pmc/articles/PMC9613403/ /pubmed/36313052 http://dx.doi.org/10.1155/2022/1633946 Text en Copyright © 2022 Yang Liu et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Liu, Yang
Tian, Meng
Liu, Ruijia
Cao, Kejing
Wang, Ruiyi
Wang, Yadi
Zhao, Wei
Zhou, Yi
Spike-Based Approximate Backpropagation Algorithm of Brain-Inspired Deep SNN for Sonar Target Classification
title Spike-Based Approximate Backpropagation Algorithm of Brain-Inspired Deep SNN for Sonar Target Classification
title_full Spike-Based Approximate Backpropagation Algorithm of Brain-Inspired Deep SNN for Sonar Target Classification
title_fullStr Spike-Based Approximate Backpropagation Algorithm of Brain-Inspired Deep SNN for Sonar Target Classification
title_full_unstemmed Spike-Based Approximate Backpropagation Algorithm of Brain-Inspired Deep SNN for Sonar Target Classification
title_short Spike-Based Approximate Backpropagation Algorithm of Brain-Inspired Deep SNN for Sonar Target Classification
title_sort spike-based approximate backpropagation algorithm of brain-inspired deep snn for sonar target classification
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9613403/
https://www.ncbi.nlm.nih.gov/pubmed/36313052
http://dx.doi.org/10.1155/2022/1633946
work_keys_str_mv AT liuyang spikebasedapproximatebackpropagationalgorithmofbraininspireddeepsnnforsonartargetclassification
AT tianmeng spikebasedapproximatebackpropagationalgorithmofbraininspireddeepsnnforsonartargetclassification
AT liuruijia spikebasedapproximatebackpropagationalgorithmofbraininspireddeepsnnforsonartargetclassification
AT caokejing spikebasedapproximatebackpropagationalgorithmofbraininspireddeepsnnforsonartargetclassification
AT wangruiyi spikebasedapproximatebackpropagationalgorithmofbraininspireddeepsnnforsonartargetclassification
AT wangyadi spikebasedapproximatebackpropagationalgorithmofbraininspireddeepsnnforsonartargetclassification
AT zhaowei spikebasedapproximatebackpropagationalgorithmofbraininspireddeepsnnforsonartargetclassification
AT zhouyi spikebasedapproximatebackpropagationalgorithmofbraininspireddeepsnnforsonartargetclassification