Meta-learning in natural and artificial intelligence

TL;DR

This paper reviews the concept of meta-learning across natural and artificial intelligence, highlighting its historical roots, current research, and future directions within neuroscience and AI.

Contribution

It offers a unified framework to understand biological and artificial meta-learning, integrating diverse research areas and proposing new interdisciplinary directions.

Findings

Meta-learning is deeply rooted in biological intelligence and cognitive science.

Recent AI and neuroscience research increasingly intersect through meta-learning.

New research directions emerge from viewing biological and artificial intelligence through meta-learning.

Abstract

Meta-learning, or learning to learn, has gained renewed interest in recent years within the artificial intelligence community. However, meta-learning is incredibly prevalent within nature, has deep roots in cognitive science and psychology, and is currently studied in various forms within neuroscience. The aim of this review is to recast previous lines of research in the study of biological intelligence within the lens of meta-learning, placing these works into a common framework. More recent points of interaction between AI and neuroscience will be discussed, as well as interesting new directions that arise under this perspective.