A Little Energy Goes a Long Way: Build an Energy-Efficient, Accurate Spiking Neural Network From Convolutional Neural Network.



Wu, Dengyu ORCID: 0000-0003-3699-4273, Yi, Xinping ORCID: 0000-0001-5163-2364 and Huang, Xiaowei ORCID: 0000-0001-6267-0366
(2022) A Little Energy Goes a Long Way: Build an Energy-Efficient, Accurate Spiking Neural Network From Convolutional Neural Network. Frontiers in neuroscience, 16. p. 759900.

Access the full-text of this item by clicking on the Open Access link.
[img] Text
A Little Energy Goes a Long Way Build an Energy-Efficient, Accurate Spiking Neural Network From Convolutional Neural Network.pdf - Published version

Download (1MB) | Preview

Abstract

This article conforms to a recent trend of developing an energy-efficient Spiking Neural Network (SNN), which takes advantage of the sophisticated training regime of Convolutional Neural Network (CNN) and converts a well-trained CNN to an SNN. We observe that the existing CNN-to-SNN conversion algorithms may keep a certain amount of residual current in the spiking neurons in SNN, and the residual current may cause significant accuracy loss when inference time is short. To deal with this, we propose a unified framework to equalize the output of the convolutional or dense layer in CNN and the accumulated current in SNN, and maximally align the spiking rate of a neuron with its corresponding charge. This framework enables us to design a novel explicit current control (ECC) method for the CNN-to-SNN conversion which considers multiple objectives at the same time during the conversion, including accuracy, latency, and energy efficiency. We conduct an extensive set of experiments on different neural network architectures, e.g., VGG, ResNet, and DenseNet, to evaluate the resulting SNNs. The benchmark datasets include not only the image datasets such as CIFAR-10/100 and ImageNet but also the Dynamic Vision Sensor (DVS) image datasets such as DVS-CIFAR-10. The experimental results show the superior performance of our ECC method over the state-of-the-art.

Item Type: Article
Uncontrolled Keywords: spiking neural network (SNN), spiking network conversion, deep learning, deep neural networks (DNNs), event-driven neural network
Divisions: Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User: Symplectic Admin
Date Deposited: 24 Jun 2022 09:38
Last Modified: 27 May 2023 09:27
DOI: 10.3389/fnins.2022.759900
Open Access URL: https://www.frontiersin.org/articles/10.3389/fnins...
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3157102