T2FSNN: Deep Spiking Neural Networks with Time-to-first-spike Coding
This addresses energy efficiency and scalability issues for SNNs in practical machine learning applications, representing an incremental improvement over existing conversion methods.
The paper tackles the inefficiency of spiking neural networks (SNNs) in terms of spike count and latency by introducing T2FSNN with time-to-first-spike coding, achieving a reduction in inference latency to 22% and spike count to less than 1% compared to state-of-the-art burst coding on CIFAR-100.
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.