Learning with Spike Synchrony in Spiking Neural Networks
This work addresses the challenge of energy-efficient computation in SNNs by leveraging biologically inspired synchronous activity, offering an incremental improvement over existing methods.
The paper tackled the problem of inefficient plasticity rules in spiking neural networks (SNNs) by introducing spike-synchrony-dependent plasticity (SSDP), which adjusts synaptic weights based on synchronous firing, resulting in improved convergence stability and robustness to spike-time jitter and event noise across various datasets.
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.