Memory-enriched computation and learning in spiking neural networks through Hebbian plasticity

TL;DR

This paper introduces a new spiking neural network architecture enriched with Hebbian plasticity, enhancing its computational and learning abilities, including generalization, one-shot learning, and cross-modal associations, with implications for energy-efficient neuromorphic hardware.

Contribution

It presents a novel Hebbian-enriched spiking neural network architecture that significantly improves diverse cognitive and learning functions compared to existing models.

Findings

Enhanced out-of-distribution generalization

Improved one-shot learning capabilities

Facilitated cross-modal generative associations

Abstract

Memory is a key component of biological neural systems that enables the retention of information over a huge range of temporal scales, ranging from hundreds of milliseconds up to years. While Hebbian plasticity is believed to play a pivotal role in biological memory, it has so far been analyzed mostly in the context of pattern completion and unsupervised learning. Here, we propose that Hebbian plasticity is fundamental for computations in biological neural systems. We introduce a novel spiking neural network architecture that is enriched by Hebbian synaptic plasticity. We show that Hebbian enrichment renders spiking neural networks surprisingly versatile in terms of their computational as well as learning capabilities. It improves their abilities for out-of-distribution generalization, one-shot learning, cross-modal generative association, language processing, and reward-based learning. As spiking neural networks are the basis for energy-efficient neuromorphic hardware, this also suggests that powerful cognitive neuromorphic systems can be build based on this principle.