Turner+et+al_2022_Neuromorph._Comput._Eng._10.1088_2634-4386_ac5ac5.pdf (851.15 kB)
mlGeNN: accelerating SNN inference using GPU-enabled neural networks
journal contribution
posted on 2023-06-10, 02:49 authored by James Turner, James KnightJames Knight, Ajay Subramanian, Thomas NowotnyThomas NowotnyIn this paper we present mlGeNN – a Python library for the conversion of arti?cial neural networks (ANNs) speci?ed in Keras to spiking neural networks (SNNs). SNNs are simulated using GeNN with extensions to e?ciently support convolutional connectivity and batching. We evaluate converted SNNs on CIFAR-10 and ImageNet classi?cation tasks and compare the performance to both the original ANNs and other SNN simulators. We ?nd 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.
History
Publication status
- Published
File Version
- Accepted version
Journal
Neuromorphic Computing and EngineeringISSN
2634-4386Publisher
IOP PublishingExternal DOI
Department affiliated with
- Informatics Publications
Research groups affiliated with
- Centre for Computational Neuroscience and Robotics Publications
Full text available
- Yes
Peer reviewed?
- Yes
Legacy Posted Date
2022-03-07First Open Access (FOA) Date
2022-03-07First Compliant Deposit (FCD) Date
2022-03-05Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC