Please use this identifier to cite or link to this item: https://doi.org/10.1145/3477145.3477157
Title: Connection Pruning for Deep Spiking Neural Networks with On-Chip Learning
Authors: Nguyen, TNN 
Veeravalli, B 
Fong, X 
Issue Date: 27-Jul-2021
Publisher: ACM
Citation: Nguyen, TNN, Veeravalli, B, Fong, X (2021-07-27). Connection Pruning for Deep Spiking Neural Networks with On-Chip Learning. ICONS 2021: International Conference on Neuromorphic Systems 2021. ScholarBank@NUS Repository. https://doi.org/10.1145/3477145.3477157
Abstract: Long training time hinders the potential of the deep, large-scale Spiking Neural Network (SNN) with the on-chip learning capability to be realized on the embedded systems hardware. Our work proposes a novel connection pruning approach that can be applied during the on-chip Spike Timing Dependent Plasticity (STDP)-based learning to optimize the learning time and the network connectivity of the deep SNN. We applied our approach to a deep SNN with the Time To First Spike (TTFS) coding and has successfully achieved 2.1x speed-up and 64% energy savings in the on-chip learning and reduced the network connectivity by 92.83%, without incurring any accuracy loss. Moreover, the connectivity reduction results in 2.83x speed-up and 78.24% energy savings in the inference. Evaluation of our proposed approach on the Field Programmable Gate Array (FPGA) platform revealed 0.56% power overhead was needed to implement the pruning algorithm.
Source Title: ICONS 2021: International Conference on Neuromorphic Systems 2021
URI: https://scholarbank.nus.edu.sg/handle/10635/245763
ISBN: 9781450386913
DOI: 10.1145/3477145.3477157
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
3477145.3477157.pdfPublished version920.01 kBAdobe PDF

CLOSED

None

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.