Unveiling the benefits of multitasking in disentangled representation formation

Jenelle Feather; SueYeon Chung

doi:10.1016/j.tics.2023.05.010

Unveiling the benefits of multitasking in disentangled representation formation

Trends Cogn Sci. 2023 Aug;27(8):699-701. doi: 10.1016/j.tics.2023.05.010. Epub 2023 Jun 23.

Authors

Jenelle Feather¹, SueYeon Chung²

Affiliations

¹ Center for Computational Neuroscience, Flatiron Institute, NY, USA; Center for Neural Science, New York University, NY, USA.
² Center for Computational Neuroscience, Flatiron Institute, NY, USA; Center for Neural Science, New York University, NY, USA. Electronic address: sueyeon@nyu.edu.

PMID: 37357063
DOI: 10.1016/j.tics.2023.05.010

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.

Publication types

Comment

MeSH terms

Humans
Mathematics
Neural Networks, Computer*