Unveiling the benefits of multitasking in disentangled representation formation
- PMID: 37357063
- DOI: 10.1016/j.tics.2023.05.010
Unveiling the benefits of multitasking in disentangled representation formation
Abstract
Johnston and Fusi recently investigated the emergence of disentangled representations when a neural network was trained to perform multiple simultaneous tasks. Such experiments explore the benefits of flexible representations and add to a growing field of research investigating the representational geometry of artificial and biological neural networks.
Copyright © 2023 The Authors. Published by Elsevier Ltd.. All rights reserved.
Conflict of interest statement
Declaration of interests No interests are declared.
Comment on
-
Abstract representations emerge naturally in neural networks trained to perform multiple tasks.Nat Commun. 2023 Feb 23;14(1):1040. doi: 10.1038/s41467-023-36583-0. Nat Commun. 2023. PMID: 36823136 Free PMC article.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources