Synchrony-Gated Plasticity with Dopamine Modulation for Spiking Neural Networks

TL;DR

This paper introduces DA-SSDP, a biologically inspired, synchrony-based local learning rule for spiking neural networks that improves accuracy on standard benchmarks with minimal additional computational cost.

Contribution

The paper presents DA-SSDP, a novel dopamine-modulated, synchrony-dependent plasticity rule that enhances training of deep SNNs without altering existing models or optimization routines.

Findings

Achieved accuracy improvements on CIFAR-10, CIFAR-100, CIFAR10-DVS, and ImageNet-1K benchmarks.

Demonstrated that a simplified synchrony rule can serve as an effective regularizer.

Provided a biologically plausible local learning mechanism compatible with supervised training.

Abstract

While surrogate backpropagation proves useful for training deep spiking neural networks (SNNs), incorporating biologically inspired local signals on a large scale remains challenging. This difficulty stems primarily from the high memory demands of maintaining accurate spike-timing logs and the potential for purely local plasticity adjustments to clash with the supervised learning goal. To effectively leverage local signals derived from spiking neuron dynamics, we introduce Dopamine-Modulated Spike-Synchrony-Dependent Plasticity (DA-SSDP), a synchrony-based rule that is sensitive to loss and brings a synchrony-based local learning signal to the model. DA-SSDP condenses spike patterns into a synchrony metric at the batch level. An initial brief warm-up phase assesses its relationship to the task loss and sets a fixed gate that subsequently adjusts the local update's magnitude. In cases where synchrony proves unrelated to the task, the gate settles at one, simplifying DA-SSDP to a basic two-factor synchrony mechanism that delivers minor weight adjustments driven by concurrent spike firing and a Gaussian latency function. These small weight updates are only added to the network`s deeper layers following the backpropagation phase, and our tests showed this simplified version did not degrade performance and sometimes gave a small accuracy boost, serving as a regularizer during training. The rule stores only binary spike indicators and first-spike latencies with a Gaussian kernel. Without altering the model structure or optimization routine, evaluations on benchmarks like CIFAR-10 (+0.42\%), CIFAR-100 (+0.99\%), CIFAR10-DVS (+0.1\%), and ImageNet-1K (+0.73\%) demonstrated consistent accuracy gains, accompanied by a minor increase in computational overhead. Our code is available at https://github.com/NeuroSyd/DA-SSDP.