Contrastive-Signal-Dependent Plasticity: Self-Supervised Learning in Spiking Neural Circuits

TL;DR

This paper introduces contrastive-signal-dependent plasticity, a biologically-inspired self-supervised learning method for spiking neural networks that enhances local synaptic adaptation and improves training efficiency.

Contribution

It proposes a novel neurobiologically-motivated learning scheme for spiking neural networks that enables effective local adaptation without extra structural components.

Findings

Outperforms other biologically-plausible learning approaches in training recurrent spiking networks.

Eliminates the need for feedback synapses in training processes.

Demonstrates consistent advantages in simulation experiments.

Abstract

Brain-inspired machine intelligence research seeks to develop computational models that emulate the information processing and adaptability that distinguishes biological systems of neurons. This has led to the development of spiking neural networks, a class of models that promisingly addresses the biological implausibility and {the lack of energy efficiency} inherent to modern-day deep neural networks. In this work, we address the challenge of designing neurobiologically-motivated schemes for adjusting the synapses of spiking networks and propose contrastive-signal-dependent plasticity, a process which generalizes ideas behind self-supervised learning to facilitate local adaptation in architectures of event-based neuronal layers that operate in parallel. Our experimental simulations demonstrate a consistent advantage over other biologically-plausible approaches when training recurrent spiking networks, crucially side-stepping the need for extra structure such as feedback synapses.