Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/107480
Title: | LC-TTFS : towards lossless network conversion for spiking neural networks with TTFS coding | Authors: | Yang, Q Zhang, M Wu, J Tan, KC Li, H |
Issue Date: | 2023 | Source: | IEEE transactions on cognitive and developmental systems, Date of Publication: 20 November 2023, Early Access, https://doi.org/10.1109/TCDS.2023.3334010 | Abstract: | The biological neurons use precise spike times, in addition to the spike firing rate, to communicate with each other. The time-to-first-spike (TTFS) coding is inspired by such biological observation. However, there is a lack of effective solutions for training TTFS-based spiking neural network (SNN). In this paper, we put forward a simple yet effective network conversion algorithm, which is referred to as LC-TTFS, by addressing two main problems that hinder an effective conversion from a high-performance artificial neural network (ANN) to a TTFS-based SNN. We show that our algorithm can achieve a near-perfect mapping between the activation values of an ANN and the spike times of an SNN on a number of challenging AI tasks, including image classification, image reconstruction, and speech enhancement. With TTFS coding, we can achieve up to orders of magnitude saving in computation over ANN and other rate-based SNNs. The study, therefore, paves the way for deploying ultra-low-power TTFS-based SNNs on power-constrained edge computing platforms. | Keywords: | ANN-to-SNN conversion Artificial neural networks Biological neural networks Computational modeling Deep spiking neural network Encoding Firing Image classification Image reconstruction Neurons Speech enhancement Task analysis Time-to-first-spike coding |
Publisher: | Institute of Electrical and Electronics Engineers | Journal: | IEEE transactions on cognitive and developmental systems | ISSN: | 2379-8920 | EISSN: | 2379-8939 | DOI: | 10.1109/TCDS.2023.3334010 |
Appears in Collections: | Journal/Magazine Article |
Show full item record
Page views
24
Citations as of Oct 13, 2024
SCOPUSTM
Citations
1
Citations as of Oct 17, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.