Supervised Spike Agreement Dependent Plasticity for Fast Local Learning in Spiking Neural Networks

TL;DR

This paper introduces a supervised, biologically plausible learning rule called SADP for spiking neural networks, enabling fast, local, and efficient supervised learning without backpropagation, demonstrated on image classification tasks.

Contribution

The paper proposes a novel supervised extension of SADP that uses population agreement metrics, improving learning speed and biological plausibility in SNNs.

Findings

Achieves competitive accuracy on standard image datasets.

Demonstrates fast convergence and stability across hyperparameters.

Compatible with device-inspired synaptic dynamics.

Abstract

Spike-Timing-Dependent Plasticity (STDP) provides a biologically grounded learning rule for spiking neural networks (SNNs), but its reliance on precise spike timing and pairwise updates limits fast learning of weights. We introduce a supervised extension of Spike Agreement-Dependent Plasticity (SADP), which replaces pairwise spike-timing comparisons with population-level agreement metrics such as Cohen's kappa. The proposed learning rule preserves strict synaptic locality, admits linear-time complexity, and enables efficient supervised learning without backpropagation, surrogate gradients, or teacher forcing. We integrate supervised SADP within hybrid CNN-SNN architectures, where convolutional encoders provide compact feature representations that are converted into Poisson spike trains for agreement-driven learning in the SNN. Extensive experiments on MNIST, Fashion-MNIST, CIFAR-10, and biomedical image classification tasks demonstrate competitive performance and fast convergence. Additional analyses show stable performance across broad hyperparameter ranges and compatibility with device-inspired synaptic update dynamics. Together, these results establish supervised SADP as a scalable, biologically grounded, and hardware-aligned learning paradigm for spiking neural networks.