Synchrony-Gated Plasticity with Dopamine Modulation for Spiking Neural Networks

2025/12/08 by Tian, Yuchen, Tensingh, Samuel, Eshraghian, Jason +2
Engineering · Neuroscience · #Advanced Memory and Neural Computing #Neural dynamics and brain function #Ferroelectric and Negative Capacitance Devices

paper · doi:10.48550/arxiv.2512.07194

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.

Citations

• Three-Factor Learning in Spiking Neural Networks: An Overview of Methods and Trends from a Machine Learning Perspective
• Toward Large-scale Spiking Neural Networks: A Comprehensive Survey and Future Directions
• Direct Training High-Performance Deep Spiking Neural Networks: A Review of Theories and Methods
• Elucidating the theoretical underpinnings of surrogate gradient learning in spiking neural networks
• QKFormer: Hierarchical Spiking Transformer using Q-K Attention
• SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks
• Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks
• Sparse-firing regularization methods for spiking neural networks with time-to-first spike coding
• Spike-driven Transformer
• Spikformer: When Spiking Neural Network Meets Transformer
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Training Deep Spiking Neural Networks using Backpropagation
• Demonstrating Hybrid Learning in a Flexible Neuromorphic Hardware System
• Rethinking the Inception Architecture for Computer Vision
• Reinforcement Learning in a Neurally Controlled Robot Using Dopamine Modulated STDP
• Spikingformer: A Key Foundation Model for Spiking Neural Networks
• Networks of spiking neurons: The third generation of neural network models

Related

• Learning with Spike Synchrony in Spiking Neural Networks
• BP-STDP: Approximating Backpropagation using Spike Timing Dependent Plasticity
• An Unsupervised STDP-based Spiking Neural Network Inspired By Biologically Plausible Learning Rules and Connections
• Desire Backpropagation: A Lightweight Training Algorithm for Multi-Layer Spiking Neural Networks based on Spike-Timing-Dependent Plasticity
• Spike Agreement Dependent Plasticity: A scalable Bio-Inspired learning paradigm for Spiking Neural Networks