LC-TTFS: Toward Lossless Network Conversion for Spiking Neural Networks With TTFS Coding
- 20 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 16 (5) , 1626-1639
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
All Related Versions
Funding Information
- National University of Singapore (I2001E0053)
- Agency for Science, Technology and Research (A18A2b0046)
- A*STAR through its RIE 2020 Advanced Manufacturing and Engineering Human (AME) Programmatic (A1687b0033)
- Research Grants Council of the Hong Kong SAR (PolyU11211521, PolyU15218622, PolyU25216423)
- Hong Kong Polytechnic University (P0039734, P0035379, P0043563, P0046094)
- National Natural Science Foundation of China (U21A20512, 62106038, 62306259)
- Sichuan Science and Technology Program (2023YFG0259)
This publication has 63 references indexed in Scilit:
- The Intel neuromorphic DNS challengeNeuromorphic Computing and Engineering, 2023
- BS4NN: Binarized Spiking Neural Networks with Temporal Coding and LearningNeural Processing Letters, 2021
- Deep Spiking Neural Network: Energy Efficiency Through Time Based Coding2020
- Mastering the game of Go without human knowledgeNature, 2017
- Noisy Softplus: A Biology Inspired Activation Function2016
- Convolutional networks for fast, energy-efficient neuromorphic computingProceedings of the National Academy of Sciences, 2016
- The tempotron: a neuron that learns spike timing–based decisionsNature Neuroscience, 2006
- Spike-based strategies for rapid processingNeural Networks, 2001
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Networks of spiking neurons: The third generation of neural network modelsNeural Networks, 1997