Continual task learning in natural and artificial agents. Issue 3 (March 2023)

• Record Type: Journal Article
• Authors: Flesch, Timo; Saxe, Andrew; Summerfield, Christopher
• Is Part Of: Trends in neurosciences. Volume 46:Issue 3(2023)
• Page Start: 199
• Page End: 210
• Publication Date: 2023-03
• Subjects: neural networks -- representational geometry -- Hebbian gating -- machine learning -- neuroimaging; Neurology -- Periodicals; Neurophysiology -- Periodicals; Neurobiology -- Periodicals; 612.8
• DOI: 10.1016/j.tins.2022.12.006
• Languages: English
• ISSNs: 0166-2236

Abstract

Highlights: Both natural and artificial agents face the challenge of learning in ways that support effective future behaviour. This may be achieved by different learning regimes, associated with distinct dynamics, and differing dimensionality and geometry of neural task representations. Where two different tasks are learned, neural codes for task-relevant information may be factorised in neocortex. Combinations of supervised and unsupervised learning mechanisms may help partition task knowledge and avoid catastrophic interference (i.e., overwriting existing knowledge). 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.