Cargando…

Going Deeper in Spiking Neural Networks: VGG and Residual Architectures

Over the past few years, Spiking Neural Networks (SNNs) have become popular as a possible pathway to enable low-power event-driven neuromorphic hardware. However, their application in machine learning have largely been limited to very shallow neural network architectures for simple problems. In this...

Descripción completa

Detalles Bibliográficos
Autores principales: Sengupta, Abhronil, Ye, Yuting, Wang, Robert, Liu, Chiao, Roy, Kaushik
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6416793/
https://www.ncbi.nlm.nih.gov/pubmed/30899212
http://dx.doi.org/10.3389/fnins.2019.00095
_version_ 1783403429515755520
author Sengupta, Abhronil
Ye, Yuting
Wang, Robert
Liu, Chiao
Roy, Kaushik
author_facet Sengupta, Abhronil
Ye, Yuting
Wang, Robert
Liu, Chiao
Roy, Kaushik
author_sort Sengupta, Abhronil
collection PubMed
description Over the past few years, Spiking Neural Networks (SNNs) have become popular as a possible pathway to enable low-power event-driven neuromorphic hardware. However, their application in machine learning have largely been limited to very shallow neural network architectures for simple problems. In this paper, we propose a novel algorithmic technique for generating an SNN with a deep architecture, and demonstrate its effectiveness on complex visual recognition problems such as CIFAR-10 and ImageNet. Our technique applies to both VGG and Residual network architectures, with significantly better accuracy than the state-of-the-art. Finally, we present analysis of the sparse event-driven computations to demonstrate reduced hardware overhead when operating in the spiking domain.
format Online
Article
Text
id pubmed-6416793
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-64167932019-03-21 Going Deeper in Spiking Neural Networks: VGG and Residual Architectures Sengupta, Abhronil Ye, Yuting Wang, Robert Liu, Chiao Roy, Kaushik Front Neurosci Neuroscience Over the past few years, Spiking Neural Networks (SNNs) have become popular as a possible pathway to enable low-power event-driven neuromorphic hardware. However, their application in machine learning have largely been limited to very shallow neural network architectures for simple problems. In this paper, we propose a novel algorithmic technique for generating an SNN with a deep architecture, and demonstrate its effectiveness on complex visual recognition problems such as CIFAR-10 and ImageNet. Our technique applies to both VGG and Residual network architectures, with significantly better accuracy than the state-of-the-art. Finally, we present analysis of the sparse event-driven computations to demonstrate reduced hardware overhead when operating in the spiking domain. Frontiers Media S.A. 2019-03-07 /pmc/articles/PMC6416793/ /pubmed/30899212 http://dx.doi.org/10.3389/fnins.2019.00095 Text en Copyright © 2019 Sengupta, Ye, Wang, Liu and Roy. http://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
Sengupta, Abhronil
Ye, Yuting
Wang, Robert
Liu, Chiao
Roy, Kaushik
Going Deeper in Spiking Neural Networks: VGG and Residual Architectures
title Going Deeper in Spiking Neural Networks: VGG and Residual Architectures
title_full Going Deeper in Spiking Neural Networks: VGG and Residual Architectures
title_fullStr Going Deeper in Spiking Neural Networks: VGG and Residual Architectures
title_full_unstemmed Going Deeper in Spiking Neural Networks: VGG and Residual Architectures
title_short Going Deeper in Spiking Neural Networks: VGG and Residual Architectures
title_sort going deeper in spiking neural networks: vgg and residual architectures
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6416793/
https://www.ncbi.nlm.nih.gov/pubmed/30899212
http://dx.doi.org/10.3389/fnins.2019.00095
work_keys_str_mv AT senguptaabhronil goingdeeperinspikingneuralnetworksvggandresidualarchitectures
AT yeyuting goingdeeperinspikingneuralnetworksvggandresidualarchitectures
AT wangrobert goingdeeperinspikingneuralnetworksvggandresidualarchitectures
AT liuchiao goingdeeperinspikingneuralnetworksvggandresidualarchitectures
AT roykaushik goingdeeperinspikingneuralnetworksvggandresidualarchitectures