Continual task learning in natural and artificial agents

TL;DR

This paper reviews recent neuroscientific and computational research on how biological and artificial agents learn new tasks, focusing on neural representations, task partitioning, and the integration of machine learning ideas.

Contribution

It synthesizes recent findings on neural representation geometry and discusses how machine learning concepts aid understanding of natural task learning in brains.

Findings

Neural representations become more task-specific during learning.

Partitioning of knowledge helps minimize interference between tasks.

Machine learning approaches provide insights into biological learning processes.

Abstract

How do humans and other animals learn new tasks? A wave of brain recording studies has investigated how neural representations change during task learning, with a focus on how tasks can be acquired and coded in ways that minimise mutual interference. We review recent work that has explored the geometry and dimensionality of neural task representations in neocortex, and computational models that have exploited these findings to understand how the brain may partition knowledge between tasks. We discuss how ideas from machine learning, including those that combine supervised and unsupervised learning, are helping neuroscientists understand how natural tasks are learned and coded in biological brains.