Spike Agreement Dependent Plasticity: A scalable Bio-Inspired learning paradigm for Spiking Neural Networks

TL;DR

This paper presents SADP, a biologically inspired, scalable learning rule for SNNs that uses population-level spike agreement metrics, outperforming classical STDP in accuracy and efficiency on standard datasets.

Contribution

Introduces SADP, a novel spike agreement-based learning rule that generalizes STDP with efficient hardware implementation and improved performance.

Findings

SADP outperforms classical STDP in accuracy on MNIST and Fashion-MNIST.

SADP has linear-time complexity suitable for hardware implementation.

Using spline-based kernels enhances SADP's performance.

Abstract

We introduce Spike Agreement Dependent Plasticity (SADP), a biologically inspired synaptic learning rule for Spiking Neural Networks (SNNs) that relies on the agreement between pre- and post-synaptic spike trains rather than precise spike-pair timing. SADP generalizes classical Spike-Timing-Dependent Plasticity (STDP) by replacing pairwise temporal updates with population-level correlation metrics such as Cohen's kappa. The SADP update rule admits linear-time complexity and supports efficient hardware implementation via bitwise logic. Empirical results on MNIST and Fashion-MNIST show that SADP, especially when equipped with spline-based kernels derived from our experimental iontronic organic memtransistor device data, outperforms classical STDP in both accuracy and runtime. Our framework bridges the gap between biological plausibility and computational scalability, offering a viable learning mechanism for neuromorphic systems.