Learning with Spike Synchrony in Spiking Neural Networks

TL;DR

This paper introduces spike-synchrony-dependent plasticity (SSDP), a novel learning rule for spiking neural networks that leverages neural synchrony to improve learning efficiency, robustness, and biological plausibility.

Contribution

The authors propose SSDP, a local, biologically inspired plasticity rule that integrates with backpropagation and enhances SNN training by utilizing neural synchrony patterns.

Findings

SSDP improves convergence stability in SNNs.

SSDP increases robustness to spike-time jitter and noise.

SSDP integrates seamlessly with existing training methods.

Abstract

Spiking neural networks (SNNs) promise energy-efficient computation by mimicking biological neural dynamics, yet existing plasticity rules focus on isolated spike pairs and fail to leverage the synchronous activity patterns that drive learning in biological systems. We introduce spike-synchrony-dependent plasticity (SSDP), a training approach that adjusts synaptic weights based on the degree of synchronous neural firing rather than spike timing order. Our method operates as a local, post-optimization mechanism that applies updates to sparse parameter subsets, maintaining computational efficiency with linear scaling. SSDP serves as a lightweight event-structure regularizer, biasing the network toward biologically plausible spatio-temporal synchrony while preserving standard convergence behavior. SSDP seamlessly integrates with standard backpropagation while preserving the forward computation graph. We validate our approach across single-layer SNNs and spiking Transformers on datasets from static images to high-temporal-resolution tasks, demonstrating improved convergence stability and enhanced robustness to spike-time jitter and event noise. These findings provide new insights into how biological neural networks might leverage synchronous activity for efficient information processing and suggest that synchrony-dependent plasticity represents a key computational principle underlying neural learning.