June 2004
Volume 4, Issue 8
Vision Sciences Society Annual Meeting Abstract  |   August 2004
Visually-guided behavior of evolved digital organisms
Author Affiliations
  • Surajit Nundy
    Duke University, USA
Journal of Vision August 2004, Vol.4, 896. doi:https://doi.org/10.1167/4.8.896
  • Views
  • Share
  • Tools
    • Alerts
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Surajit Nundy, Dale Purves; Visually-guided behavior of evolved digital organisms. Journal of Vision 2004;4(8):896. https://doi.org/10.1167/4.8.896.

      Download citation file:

      © ARVO (1962-2015); The Authors (2016-present)

  • Supplements

Unsupervised digital organisms guided by artificial neural networks were allowed to evolve in virtual environments based solely on the success or failure of their responses to visual input. The criteria of success were avoiding collisions with surfaces and fully exploring the environment. The results showed that: 1) visually-guided behavior improved over successive generations; 2) organisms that evolved in one environment showed improved behavior in a novel environment; 3) the improved behavior was influenced by the image-source relationships they had experienced; 4) the improved behavior was influenced by the dynamic structure of visual input in the absence of any explicit model of memory; and 5) the improved behavior of the organisms was resistant to random modification of their neural networks. These observations show that increasingly successful visually-guided behavior can be generated simply by the incorporation into neural networks of the statistical relationship between images and their underlying sources.

Nundy, S., Purves, D.(2004). Visually-guided behavior of evolved digital organisms [Abstract]. Journal of Vision, 4( 8): 896, 896a, http://journalofvision.org/4/8/896/, doi:10.1167/4.8.896. [CrossRef]

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.