EchoSpike Predictive Plasticity: An Online Local Learning Rule for Spiking Neural Networks

TL;DR

This paper introduces EchoSpike Predictive Plasticity, a novel online local learning rule for spiking neural networks that enables efficient, self-supervised, hierarchical learning suitable for low-power neuromorphic hardware.

Contribution

It proposes the ESPP learning rule, the first to leverage hierarchical temporal dynamics for online local learning in multi-layer SNNs, advancing biologically plausible self-supervised learning.

Findings

Performs on par with state-of-the-art supervised methods

Effective for low-cost neuromorphic processors

Enhances online adaptive learning in SNNs

Abstract

The drive to develop artificial neural networks that efficiently utilize resources has generated significant interest in bio-inspired Spiking Neural Networks (SNNs). These networks are particularly attractive due to their potential in applications requiring low power and memory. This potential is further enhanced by the ability to perform online local learning, enabling them to adapt to dynamic environments. This requires the model to be adaptive in a self-supervised manner. While self-supervised learning has seen great success in many deep learning domains, its application for online local learning in multi-layer SNNs remains underexplored. In this paper, we introduce the "EchoSpike Predictive Plasticity" (ESPP) learning rule, a pioneering online local learning rule designed to leverage hierarchical temporal dynamics in SNNs through predictive and contrastive coding. We validate the effectiveness of this approach using benchmark datasets, demonstrating that it performs on par with current state-of-the-art supervised learning rules. The temporal and spatial locality of ESPP makes it particularly well-suited for low-cost neuromorphic processors, representing a significant advancement in developing biologically plausible self-supervised learning models for neuromorphic computing at the edge.