mlGeNN: accelerating SNN inference using GPU-enabled neural networks

Turner, James Paul, Knight, James Courtney, Subramanian, Ajay and Nowotny, Thomas (2022) mlGeNN: accelerating SNN inference using GPU-enabled neural networks. Neuromorphic Computing and Engineering. ISSN 2634-4386

[img] PDF - Accepted Version
Available under License Creative Commons Attribution.

Download (871kB)

Abstract

In this paper we present mlGeNN – a Python library for the conversion of artificial neural networks (ANNs) specified in Keras to spiking neural networks (SNNs). SNNs are simulated using GeNN with extensions to efficiently support convolutional connectivity and batching. We evaluate converted SNNs on CIFAR-10 and ImageNet classification tasks and compare the performance to both the original ANNs and other SNN simulators. We find that performing inference using a VGG-16 model, trained on the CIFAR-10 dataset, is 2.5× faster than BindsNet and, when using a ResNet-20 model trained on CIFAR-10 with FewSpike ANN to SNN conversion, mlGeNN is only a little over 2× slower than TensorFlow.

Item Type: Article
Schools and Departments: School of Engineering and Informatics > Informatics
Research Centres and Groups: Centre for Computational Neuroscience and Robotics
SWORD Depositor: Mx Elements Account
Depositing User: Mx Elements Account
Date Deposited: 07 Mar 2022 08:33
Last Modified: 07 Mar 2022 08:45
URI: http://sro.sussex.ac.uk/id/eprint/104723

View download statistics for this item

📧 Request an update