A Deep Convolutional Spiking Neural Network for embedded applications

Javanshir, A; Nguyen, TT; Mahmud, MAP; Kouzani, AZ

A Deep Convolutional Spiking Neural Network for embedded applications

Javanshir, A Nguyen, TT Mahmud, MAP Kouzani, AZ

Permalink

Publisher:: SPRINGERNATURE
Publication Type:: Journal Article
Citation:: PROGRESS IN ARTIFICIAL INTELLIGENCE, 2024, 13, (1), pp. 1-15
Issue Date:: 2024-03

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (1.66 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Javanshir, A
dc.contributor.author	Nguyen, TT
dc.contributor.author	Mahmud, MAP
dc.contributor.author	Kouzani, AZ
dc.date.accessioned	2024-12-16T00:00:53Z
dc.date.available	2024-12-16T00:00:53Z
dc.date.issued	2024-03
dc.identifier.citation	PROGRESS IN ARTIFICIAL INTELLIGENCE, 2024, 13, (1), pp. 1-15
dc.identifier.issn	2192-6352
dc.identifier.issn	2192-6360
dc.identifier.uri	http://hdl.handle.net/10453/182539
dc.description.abstract	<jats:title>Abstract</jats:title><jats:p>Deep neural networks (DNNs) have received a great deal of interest in solving everyday tasks in recent years. However, their computational and energy costs limit their use on mobile and edge devices. The neuromorphic computing approach called spiking neural networks (SNNs) represents a potential solution for bridging the gap between performance and computational expense. Despite the potential benefits of energy efficiency, the current SNNs are being used with datasets such as MNIST, Fashion-MNIST, and CIFAR10, limiting their applications compared to DNNs. Therefore, the applicability of SNNs to real-world applications, such as scene classification and forecasting epileptic seizures, must be demonstrated yet. This paper develops a deep convolutional spiking neural network (DCSNN) for embedded applications. We explore a convolutional architecture, Visual Geometry Group (VGG16), to implement deeper SNNs. To train a spiking model, we convert the pre-trained VGG16 into corresponding spiking equivalents with nearly comparable performance to the original one. The trained weights of VGG16 were then transferred to the equivalent SNN architecture while performing a proper weight–threshold balancing. The model is evaluated in two case studies: land use and land cover classification, and epileptic seizure detection. Experimental results show a classification accuracy of 94.88%, and seizure detection specificity of 99.45% and a sensitivity of 95.06%. It is confirmed that conversion-based training SNNs are promising, and the benefits of DNNs, such as solving complex and real-world problems, become available to SNNs.</jats:p>
dc.language	English
dc.publisher	SPRINGERNATURE
dc.relation.ispartof	PROGRESS IN ARTIFICIAL INTELLIGENCE
dc.relation.isbasedon	10.1007/s13748-024-00313-4
dc.rights	info:eu-repo/semantics/openAccess
dc.title	A Deep Convolutional Spiking Neural Network for embedded applications
dc.type	Journal Article
utslib.citation.volume	13
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Science
pubs.organisational-group	University of Technology Sydney/Faculty of Science/School of Mathematical and Physical Sciences
utslib.copyright.status	open_access	*
dc.rights.license	This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/
dc.date.updated	2024-12-16T00:00:51Z
pubs.issue	1
pubs.publication-status	Published
pubs.volume	13
utslib.citation.issue	1

Abstract:

AbstractDeep neural networks (DNNs) have received a great deal of interest in solving everyday tasks in recent years. However, their computational and energy costs limit their use on mobile and edge devices. The neuromorphic computing approach called spiking neural networks (SNNs) represents a potential solution for bridging the gap between performance and computational expense. Despite the potential benefits of energy efficiency, the current SNNs are being used with datasets such as MNIST, Fashion-MNIST, and CIFAR10, limiting their applications compared to DNNs. Therefore, the applicability of SNNs to real-world applications, such as scene classification and forecasting epileptic seizures, must be demonstrated yet. This paper develops a deep convolutional spiking neural network (DCSNN) for embedded applications. We explore a convolutional architecture, Visual Geometry Group (VGG16), to implement deeper SNNs. To train a spiking model, we convert the pre-trained VGG16 into corresponding spiking equivalents with nearly comparable performance to the original one. The trained weights of VGG16 were then transferred to the equivalent SNN architecture while performing a proper weight–threshold balancing. The model is evaluated in two case studies: land use and land cover classification, and epileptic seizure detection. Experimental results show a classification accuracy of 94.88%, and seizure detection specificity of 99.45% and a sensitivity of 95.06%. It is confirmed that conversion-based training SNNs are promising, and the benefits of DNNs, such as solving complex and real-world problems, become available to SNNs.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/182539