Event-driven eligibility propagation in large sparse networks: efficiency shaped by biological realism

TL;DR

This paper introduces a biologically plausible, event-driven learning rule for large-scale recurrent spiking neural networks, demonstrating its efficiency and scalability in neuromorphic tasks while incorporating key biological features.

Contribution

It extends eligibility propagation to an event-driven framework with biological realism, enabling scalable, efficient learning in large neural networks.

Findings

Effective learning in neuromorphic MNIST tasks

Scalability to millions of neurons without performance loss

Biologically grounded constraints improve computational efficiency

Abstract

Despite remarkable technological advances, AI systems may still benefit from biological principles, such as recurrent connectivity and energy-efficient mechanisms. Drawing inspiration from the brain, we present a biologically plausible extension of the eligibility propagation (e-prop) learning rule for recurrent spiking networks. By translating the time-driven update scheme into an event-driven one, we integrate the learning rule into a simulation platform for large-scale spiking neural networks and demonstrate its applicability to tasks such as neuromorphic MNIST. We extend the model with prominent biological features such as continuous dynamics and weight updates, strict locality, and sparse connectivity. Our results show that biologically grounded constraints can inform the design of computationally efficient AI algorithms, offering scalability to millions of neurons without compromising learning performance. This work bridges machine learning and computational neuroscience, paving the way for sustainable, biologically inspired AI systems while advancing our understanding of brain-like learning.