Brain-Inspired Architecture for Spiking Neural Networks

Spiking neural networks (SNNs), using action potentials (spikes) to represent and transmit information, are more biologically plausible than traditional artificial neural networks. However, most of the existing SNNs require a separate preprocessing step to convert the real-valued input into spikes t...

Full description

Saved in:
Bibliographic Details
Main Authors: Fengzhen Tang, Junhuai Zhang, Chi Zhang, Lianqing Liu
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Biomimetics
Subjects:
Online Access:https://www.mdpi.com/2313-7673/9/10/646
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204689374642176
author Fengzhen Tang
Junhuai Zhang
Chi Zhang
Lianqing Liu
author_facet Fengzhen Tang
Junhuai Zhang
Chi Zhang
Lianqing Liu
author_sort Fengzhen Tang
collection DOAJ
description Spiking neural networks (SNNs), using action potentials (spikes) to represent and transmit information, are more biologically plausible than traditional artificial neural networks. However, most of the existing SNNs require a separate preprocessing step to convert the real-valued input into spikes that are then input to the network for processing. The dissected spike-coding process may result in information loss, leading to degenerated performance. However, the biological neuron system does not perform a separate preprocessing step. Moreover, the nervous system may not have a single pathway with which to respond and process external stimuli but allows multiple circuits to perceive the same stimulus. Inspired by these advantageous aspects of the biological neural system, we propose a self-adaptive encoding spike neural network with parallel architecture. The proposed network integrates the input-encoding process into the spiking neural network architecture via convolutional operations such that the network can accept the real-valued input and automatically transform it into spikes for further processing. Meanwhile, the proposed network contains two identical parallel branches, inspired by the biological nervous system that processes information in both serial and parallel. The experimental results on multiple image classification tasks reveal that the proposed network can obtain competitive performance, suggesting the effectiveness of the proposed architecture.
format Article
id doaj-art-865d8769ab3041eeaaaeea2116d0eb13
institution OA Journals
issn 2313-7673
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Biomimetics
spelling doaj-art-865d8769ab3041eeaaaeea2116d0eb132025-08-20T02:11:14ZengMDPI AGBiomimetics2313-76732024-10-0191064610.3390/biomimetics9100646Brain-Inspired Architecture for Spiking Neural NetworksFengzhen Tang0Junhuai Zhang1Chi Zhang2Lianqing Liu3State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Nanta Street 114, Shenyang 110016, ChinaState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Nanta Street 114, Shenyang 110016, ChinaState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Nanta Street 114, Shenyang 110016, ChinaState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Nanta Street 114, Shenyang 110016, ChinaSpiking neural networks (SNNs), using action potentials (spikes) to represent and transmit information, are more biologically plausible than traditional artificial neural networks. However, most of the existing SNNs require a separate preprocessing step to convert the real-valued input into spikes that are then input to the network for processing. The dissected spike-coding process may result in information loss, leading to degenerated performance. However, the biological neuron system does not perform a separate preprocessing step. Moreover, the nervous system may not have a single pathway with which to respond and process external stimuli but allows multiple circuits to perceive the same stimulus. Inspired by these advantageous aspects of the biological neural system, we propose a self-adaptive encoding spike neural network with parallel architecture. The proposed network integrates the input-encoding process into the spiking neural network architecture via convolutional operations such that the network can accept the real-valued input and automatically transform it into spikes for further processing. Meanwhile, the proposed network contains two identical parallel branches, inspired by the biological nervous system that processes information in both serial and parallel. The experimental results on multiple image classification tasks reveal that the proposed network can obtain competitive performance, suggesting the effectiveness of the proposed architecture.https://www.mdpi.com/2313-7673/9/10/646spiking neural networksself-adaptive codingsurrogate gradient backpropagationleaky integrate-and-fire neuron model
spellingShingle Fengzhen Tang
Junhuai Zhang
Chi Zhang
Lianqing Liu
Brain-Inspired Architecture for Spiking Neural Networks
Biomimetics
spiking neural networks
self-adaptive coding
surrogate gradient backpropagation
leaky integrate-and-fire neuron model
title Brain-Inspired Architecture for Spiking Neural Networks
title_full Brain-Inspired Architecture for Spiking Neural Networks
title_fullStr Brain-Inspired Architecture for Spiking Neural Networks
title_full_unstemmed Brain-Inspired Architecture for Spiking Neural Networks
title_short Brain-Inspired Architecture for Spiking Neural Networks
title_sort brain inspired architecture for spiking neural networks
topic spiking neural networks
self-adaptive coding
surrogate gradient backpropagation
leaky integrate-and-fire neuron model
url https://www.mdpi.com/2313-7673/9/10/646
work_keys_str_mv AT fengzhentang braininspiredarchitectureforspikingneuralnetworks
AT junhuaizhang braininspiredarchitectureforspikingneuralnetworks
AT chizhang braininspiredarchitectureforspikingneuralnetworks
AT lianqingliu braininspiredarchitectureforspikingneuralnetworks