Cargando…

Spiking neural network with working memory can integrate and rectify spatiotemporal features

In the real world, information is often correlated with each other in the time domain. Whether it can effectively make a decision according to the global information is the key indicator of information processing ability. Due to the discrete characteristics of spike trains and unique temporal dynami...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Yi, Liu, Hanwen, Shi, Kexin, Zhang, Malu, Qu, Hong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10300445/
https://www.ncbi.nlm.nih.gov/pubmed/37389360
http://dx.doi.org/10.3389/fnins.2023.1167134
_version_ 1785064590789312512
author Chen, Yi
Liu, Hanwen
Shi, Kexin
Zhang, Malu
Qu, Hong
author_facet Chen, Yi
Liu, Hanwen
Shi, Kexin
Zhang, Malu
Qu, Hong
author_sort Chen, Yi
collection PubMed
description In the real world, information is often correlated with each other in the time domain. Whether it can effectively make a decision according to the global information is the key indicator of information processing ability. Due to the discrete characteristics of spike trains and unique temporal dynamics, spiking neural networks (SNNs) show great potential in applications in ultra-low-power platforms and various temporal-related real-life tasks. However, the current SNNs can only focus on the information a short time before the current moment, its sensitivity in the time domain is limited. This problem affects the processing ability of SNN in different kinds of data, including static data and time-variant data, and reduces the application scenarios and scalability of SNN. In this work, we analyze the impact of such information loss and then integrate SNN with working memory inspired by recent neuroscience research. Specifically, we propose Spiking Neural Networks with Working Memory (SNNWM) to handle input spike trains segment by segment. On the one hand, this model can effectively increase SNN's ability to obtain global information. On the other hand, it can effectively reduce the information redundancy between adjacent time steps. Then, we provide simple methods to implement the proposed network architecture from the perspectives of biological plausibility and neuromorphic hardware friendly. Finally, we test the proposed method on static and sequential data sets, and the experimental results show that the proposed model can better process the whole spike train, and achieve state-of-the-art results in short time steps. This work investigates the contribution of introducing biologically inspired mechanisms, e.g., working memory, and multiple delayed synapses to SNNs, and provides a new perspective to design future SNNs.
format Online
Article
Text
id pubmed-10300445
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-103004452023-06-29 Spiking neural network with working memory can integrate and rectify spatiotemporal features Chen, Yi Liu, Hanwen Shi, Kexin Zhang, Malu Qu, Hong Front Neurosci Neuroscience In the real world, information is often correlated with each other in the time domain. Whether it can effectively make a decision according to the global information is the key indicator of information processing ability. Due to the discrete characteristics of spike trains and unique temporal dynamics, spiking neural networks (SNNs) show great potential in applications in ultra-low-power platforms and various temporal-related real-life tasks. However, the current SNNs can only focus on the information a short time before the current moment, its sensitivity in the time domain is limited. This problem affects the processing ability of SNN in different kinds of data, including static data and time-variant data, and reduces the application scenarios and scalability of SNN. In this work, we analyze the impact of such information loss and then integrate SNN with working memory inspired by recent neuroscience research. Specifically, we propose Spiking Neural Networks with Working Memory (SNNWM) to handle input spike trains segment by segment. On the one hand, this model can effectively increase SNN's ability to obtain global information. On the other hand, it can effectively reduce the information redundancy between adjacent time steps. Then, we provide simple methods to implement the proposed network architecture from the perspectives of biological plausibility and neuromorphic hardware friendly. Finally, we test the proposed method on static and sequential data sets, and the experimental results show that the proposed model can better process the whole spike train, and achieve state-of-the-art results in short time steps. This work investigates the contribution of introducing biologically inspired mechanisms, e.g., working memory, and multiple delayed synapses to SNNs, and provides a new perspective to design future SNNs. Frontiers Media S.A. 2023-06-14 /pmc/articles/PMC10300445/ /pubmed/37389360 http://dx.doi.org/10.3389/fnins.2023.1167134 Text en Copyright © 2023 Chen, Liu, Shi, Zhang and Qu. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Chen, Yi
Liu, Hanwen
Shi, Kexin
Zhang, Malu
Qu, Hong
Spiking neural network with working memory can integrate and rectify spatiotemporal features
title Spiking neural network with working memory can integrate and rectify spatiotemporal features
title_full Spiking neural network with working memory can integrate and rectify spatiotemporal features
title_fullStr Spiking neural network with working memory can integrate and rectify spatiotemporal features
title_full_unstemmed Spiking neural network with working memory can integrate and rectify spatiotemporal features
title_short Spiking neural network with working memory can integrate and rectify spatiotemporal features
title_sort spiking neural network with working memory can integrate and rectify spatiotemporal features
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10300445/
https://www.ncbi.nlm.nih.gov/pubmed/37389360
http://dx.doi.org/10.3389/fnins.2023.1167134
work_keys_str_mv AT chenyi spikingneuralnetworkwithworkingmemorycanintegrateandrectifyspatiotemporalfeatures
AT liuhanwen spikingneuralnetworkwithworkingmemorycanintegrateandrectifyspatiotemporalfeatures
AT shikexin spikingneuralnetworkwithworkingmemorycanintegrateandrectifyspatiotemporalfeatures
AT zhangmalu spikingneuralnetworkwithworkingmemorycanintegrateandrectifyspatiotemporalfeatures
AT quhong spikingneuralnetworkwithworkingmemorycanintegrateandrectifyspatiotemporalfeatures