Theories of synaptic memory consolidation and intelligent plasticity for continual learning

TL;DR

This paper explores how complex synaptic dynamics and internal states enable continual learning in neural networks, emphasizing the importance of plasticity mechanisms and synaptic metaplasticity for lifelong intelligence.

Contribution

It provides a comprehensive survey of theoretical models highlighting internal synaptic states and metaplasticity as key to continual learning in artificial and biological systems.

Findings

Synaptic internal states are crucial for lifelong learning.

Plasticity algorithms leveraging internal states improve memory retention.

Synaptic metaplasticity sustains continual learning capabilities.

Abstract

Humans and animals learn throughout life. Such continual learning is crucial for intelligence. In this chapter, we examine the pivotal role plasticity mechanisms with complex internal synaptic dynamics could play in enabling this ability in neural networks. By surveying theoretical research, we highlight two fundamental enablers for continual learning. First, synaptic plasticity mechanisms must maintain and evolve an internal state over several behaviorally relevant timescales. Second, plasticity algorithms must leverage the internal state to intelligently regulate plasticity at individual synapses to facilitate the seamless integration of new memories while avoiding detrimental interference with existing ones. Our chapter covers successful applications of these principles to deep neural networks and underscores the significance of synaptic metaplasticity in sustaining continual learning capabilities. Finally, we outline avenues for further research to understand the brain's superb continual learning abilities and harness similar mechanisms for artificial intelligence systems.