Header

UZH-Logo

Maintenance Infos

Optimizing the Energy Consumption of Spiking Neural Networks for Neuromorphic Applications


Sorbaro, Martino; Liu, Qian; Bortone, Massimo; Sheik, Sadique (2020). Optimizing the Energy Consumption of Spiking Neural Networks for Neuromorphic Applications. Frontiers in Neuroscience, 14:662.

Abstract

In the last few years, spiking neural networks (SNNs) have been demonstrated to perform on par with regular convolutional neural networks. Several works have proposed methods to convert a pre-trained CNN to a Spiking CNN without a significant sacrifice of performance. We demonstrate first that quantization-aware training of CNNs leads to better accuracy in SNNs. One of the benefits of converting CNNs to spiking CNNs is to leverage the sparse computation of SNNs and consequently perform equivalent computation at a lower energy consumption. Here we propose an optimization strategy to train efficient spiking networks with lower energy consumption, while maintaining similar accuracy levels. We demonstrate results on the MNIST-DVS and CIFAR-10 datasets.

Abstract

In the last few years, spiking neural networks (SNNs) have been demonstrated to perform on par with regular convolutional neural networks. Several works have proposed methods to convert a pre-trained CNN to a Spiking CNN without a significant sacrifice of performance. We demonstrate first that quantization-aware training of CNNs leads to better accuracy in SNNs. One of the benefits of converting CNNs to spiking CNNs is to leverage the sparse computation of SNNs and consequently perform equivalent computation at a lower energy consumption. Here we propose an optimization strategy to train efficient spiking networks with lower energy consumption, while maintaining similar accuracy levels. We demonstrate results on the MNIST-DVS and CIFAR-10 datasets.

Statistics

Citations

Altmetrics

Downloads

1 download since deposited on 16 Feb 2021
1 download since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Scopus Subject Areas:Life Sciences > General Neuroscience
Language:English
Date:30 June 2020
Deposited On:16 Feb 2021 09:22
Last Modified:01 Mar 2021 16:31
Publisher:Frontiers Research Foundation
ISSN:1662-453X
OA Status:Gold
Free access at:PubMed ID. An embargo period may apply.
Publisher DOI:https://doi.org/10.3389/fnins.2020.00662
PubMed ID:32694978

Download

Gold Open Access

Download PDF  'Optimizing the Energy Consumption of Spiking Neural Networks for Neuromorphic Applications'.
Preview
Content: Published Version
Filetype: PDF
Size: 1MB
View at publisher
Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)