Generative adversarial networks unlock new methods for cognitive science.

Journal: Trends in cognitive sciences
Published Date:

Abstract

Generative adversarial networks (GANs) enable computers to learn complex data distributions and sample from these distributions. When applied to the visual domain, this allows artificial, yet photorealistic images to be synthesized. Their success at this very challenging task triggered an explosion of research within the field of artificial intelligence (AI), yielding various new GAN findings and applications. After explaining the core principles behind GANs and reviewing recent GAN innovations, we illustrate how they can be applied to tackle thorny theoretical and methodological problems in cognitive science. We focus on how GANs can reveal hidden structure in internal representations and how they offer a valuable new compromise in the trade-off between experimental control and ecological validity.

Authors

  • Lore Goetschalckx
    Department of Brain and Cognition, KU Leuven, 3000 Leuven, Belgium; Carney Institute for Brain Science, Department of Cognitive Linguistic & Psychological Sciences, Brown University, Providence, RI 02912, USA. Electronic address: lore_goetschalckx@brown.edu.
  • Alex Andonian
    Computer Science and Artificial Intelligence Laboratory (CSAIL), MIT, Cambridge, MA 02139, USA.
  • Johan Wagemans
    Department of Brain and Cognition, KU Leuven, 3000 Leuven, Belgium.