Exploring Tradeoffs in Spiking Neural Networks

TL;DR

This paper investigates the tradeoffs in Spiking Neural Networks constrained by time-to-first-spike, and proposes a relaxed approach allowing multiple spikes to improve performance, robustness, and convergence speed.

Contribution

It introduces a relaxed spike constraint in SNNs, demonstrating improved performance and robustness over TTFS-constrained models.

Findings

Relaxed spike constraints lead to higher accuracy.

Unconstrained SNNs converge faster and are more noise-robust.

Tradeoffs exist between performance, latency, and sparsity.

Abstract

Spiking Neural Networks (SNNs) have emerged as a promising alternative to traditional Deep Neural Networks for low-power computing. However, the effectiveness of SNNs is not solely determined by their performance but also by their energy consumption, prediction speed, and robustness to noise. The recent method Fast \& Deep, along with others, achieves fast and energy-efficient computation by constraining neurons to fire at most once. Known as Time-To-First-Spike (TTFS), this constraint however restricts the capabilities of SNNs in many aspects. In this work, we explore the relationships between performance, energy consumption, speed and stability when using this constraint. More precisely, we highlight the existence of tradeoffs where performance and robustness are gained at the cost of sparsity and prediction latency. To improve these tradeoffs, we propose a relaxed version of Fast \& Deep that allows for multiple spikes per neuron. Our experiments show that relaxing the spike constraint provides higher performance while also benefiting from faster convergence, similar sparsity, comparable prediction latency, and better robustness to noise compared to TTFS SNNs. By highlighting the limitations of TTFS and demonstrating the advantages of unconstrained SNNs we provide valuable insight for the development of effective learning strategies for neuromorphic computing.