Generative adversarial networks unlock new methods for cognitive science

Trends Cogn Sci. 2021 Sep;25(9):788-801. doi: 10.1016/j.tics.2021.06.006. Epub 2021 Aug 4.


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.

Keywords: experimental control; generative adversarial networks; image synthesis; natural images; visual stimuli.

Publication types

  • Research Support, Non-U.S. Gov't
  • Review

MeSH terms

  • Artificial Intelligence*
  • Cognitive Science
  • Computers
  • Humans
  • Image Processing, Computer-Assisted*
  • Neural Networks, Computer