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.

翻译：脉冲神经网络（SNNs）作为传统深度神经网络的低功耗计算替代方案，近年来备受关注。然而，SNNs的有效性不仅取决于其性能，还涉及能耗、预测速度及噪声鲁棒性等关键指标。近期提出的Fast & Deep方法及其同类技术通过限制神经元最多发放一次脉冲，实现了快速且节能的计算。但这种被称为"首次脉冲时间编码"（TTFS）的约束条件，在多个维度上限制了SNN的能力。本研究系统考察了采用该约束时性能、能耗、速度与稳定性之间的关联关系，重点揭示了性能与鲁棒性提升伴随稀疏性与预测延迟代价的权衡现象。为改善这些权衡关系，我们提出Fast & Deep的松弛化版本，允许每个神经元发放多次脉冲。实验表明，相较于TTFS-SNN，这种松弛约束不仅带来更高的性能表现，还实现了更快的收敛速度、相当的稀疏性、可比的预测延迟以及更强的噪声鲁棒性。通过揭示TTFS的局限性并论证无约束SNN的优势，本研究为神经形态计算有效学习策略的开发提供了重要启示。