Temporal-Coded Spiking Neural Networks with Dynamic Firing Threshold: Learning with Event-Driven Backpropagation

Wenjie Wei, Malu Zhang*, Hong Qu, Ammar Belatreche, Jian Zhang, Hong Chen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)
82 Downloads (Pure)

Abstract

Spiking Neural Networks (SNNs) offer a highly promising computing paradigm due to their biological plausibility, exceptional spatiotemporal information processing capability and low power consumption. As a temporal encoding scheme for SNNs, Time-To-First-Spike (TTFS) encodes information using the timing of a single spike, which allows spiking neurons to transmit information through sparse spike trains and results in lower power consumption and higher computational efficiency compared to traditional rate-based encoding counterparts. However, despite the advantages of the TTFS encoding scheme, the effective and efficient training of TTFS-based deep SNNs remains a significant and open research problem. In this work, we first examine the factors underlying the limitations of applying existing TTFS-based learning algorithms to deep SNNs. Specifically, we investigate the issues related to oversparsity of spikes and the complexity of finding the ‘causal set’. We then propose a simple yet efficient dynamic firing threshold (DFT) mechanism for spiking neurons to address these issues. Building upon the proposed DFT mechanism, we further introduce a novel direct training algorithm for TTFS-based deep SNNs, called DTA-TTFS. This method utilizes event-driven processing and spike timing to enable efficient learning of deep SNNs. The proposed training method was validated on image classification and the experimental results clearly demonstrate that our proposed method achieves state-of-the-art accuracy in comparison to existing TTFS-based learning algorithms, while maintaining high levels of sparsity and energy efficiency on neuromorphic inference accelerator.
Original languageEnglish
Title of host publicationProceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV 2023)
Subtitle of host publicationParis, France, 2-6 October 2023
Place of PublicationPiscataway, US
PublisherIEEE
Pages10518-10528
Number of pages11
ISBN (Electronic)9798350307184
ISBN (Print)9798350307191
DOIs
Publication statusPublished - 1 Oct 2023
EventInternational Conference on Computer Vision 2023 - Paris Convention Centre, Paris, France
Duration: 2 Oct 20236 Oct 2023
https://iccv2023.thecvf.com/

Conference

ConferenceInternational Conference on Computer Vision 2023
Abbreviated titleICCV 2023
Country/TerritoryFrance
CityParis
Period2/10/236/10/23
Internet address

Cite this