Structural features of the fly olfactory circuit mitigate the stability-plasticity dilemma in continual learning

TL;DR

This paper introduces a biologically inspired fly olfactory circuit model that improves continual learning in neural networks by balancing memory stability and plasticity, validated across multiple datasets.

Contribution

The study presents the Fly Model, a plug-and-play biological circuit component that enhances continual learning in neural networks with minimal computational overhead.

Findings

The Fly Model improves memory stability and plasticity in continual learning.

It effectively overcomes limitations of existing strategies in challenging scenarios.

Validated across various datasets, demonstrating broad applicability.

Abstract

Artificial neural networks face the stability-plasticity dilemma in continual learning, while the brain can maintain memories and remain adaptable. However, the biological strategies for continual learning and their potential to inspire learning algorithms in neural networks are poorly understood. This study presents a minimal model of the fly olfactory circuit to investigate the biological strategies that support continual odor learning. We introduce the fly olfactory circuit as a plug-and-play component, termed the Fly Model, which can integrate with modern machine learning methods to address this dilemma. Our findings demonstrate that the Fly Model enhances both memory stability and learning plasticity, overcoming the limitations of current continual learning strategies. We validated its effectiveness across various challenging continual learning scenarios using commonly used datasets. The fly olfactory system serves as an elegant biological circuit for lifelong learning, offering a module that enhances continual learning with minimal additional computational cost for machine learning.