Unveiling the benefits of multitasking in disentangled representation formation.

Journal: Trends in cognitive sciences
Published Date: Aug 1, 2023

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.

Authors

  • Jenelle Feather
    Center for Computational Neuroscience, Flatiron Institute, NY, USA; Center for Neural Science, New York University, NY, USA.
  • SueYeon Chung
    Program in Applied Physics, School of Engineering and Applied Sciences, Harvard University, Cambridge, Massachusetts 02138, USA.

Keywords

External Resources

Popular Topics
Recent Journals