Publications
Detailed Information
T2FSNN: Deep Spiking Neural Networks with Time-to-first-spike Coding
Cited 40 time in
Web of Science
Cited 66 time in Scopus
- Authors
- Issue Date
- 2020-07
- Publisher
- IEEE
- Citation
- PROCEEDINGS OF THE 2020 57TH ACM/EDAC/IEEE DESIGN AUTOMATION CONFERENCE (DAC), p. 9218689
- Abstract
- Spiking neural networks (SNNs) have gained considerable interest due to their energy-efficient characteristics, yet lack of a scalable training algorithm has restricted their applicability in practical machine learning problems. The deep neural network-to-SNN conversion approach has been widely studied to broaden the applicability of SNNs. Most previous studies, however, have not fully utilized spatio-temporal aspects of SNNs, which has led to inefficiency in terms of number of spikes and inference latency. In this paper, we present T2FSNN, which introduces the concept of time-to-first-spike coding into deep SNNs using the kernel-based dynamic threshold and dendrite to overcome the aforementioned drawback. In addition, we propose gradient-based optimization and early firing methods to further increase the efficiency of the T2FSNN. According to our results, the proposed methods can reduce inference latency and number of spikes to 22% and less than 1%, compared to those of burst coding, which is the state-of-the-art result on the CIFAR-100.
- ISSN
- 0738-100X
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.