Meta-learning in natural and artificial intelligence
This paper provides a unifying framework for understanding meta-learning across biological and artificial intelligence, which is significant for researchers in AI, neuroscience, and cognitive science.
This paper reviews the concept of meta-learning, or learning to learn, by examining its prevalence in natural intelligence, cognitive science, psychology, and neuroscience. It aims to unify previous research in biological intelligence under a meta-learning framework and discusses recent interactions between AI and neuroscience.
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.