Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks

Abstract

For the gradient computation across the time domain in Spiking Neural Networks (SNNs) training, two different approaches have been independently studied. The first is to compute the gradients with respect to the change in spike activation (activation-based methods), and the second is to compute the gradients with respect to the change in spike timing (timing-based methods). In this work, we present a comparative study of the two methods and propose a new supervised learning method that combines them. The proposed method utilizes each individual spike more effectively by shifting spike timings as in the timing-based methods as well as generating and removing spikes as in the activation-based methods. Experimental results showed that the proposed method achieves higher performance in terms of both accuracy and efficiency than the previous approaches.

arXiv commentTo be published in NeurIPS 2020

References in corpus (6)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
• Binarized Neural Networks
• SLAYER: Spike Layer Error Reassignment in Time
• Spiking Deep Networks with LIF Neurons
• Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks

Cited by in corpus (2)

• Training Energy-Efficient Deep Spiking Neural Networks with Time-to-First-Spike Coding
• Effects of VLSI Circuit Constraints on Temporal-Coding Multilayer Spiking Neural Networks