Evolution of visually guided behavior in artificial agents.

Journal Article

Recent work on brightness, color, and form has suggested that human visual percepts represent the probable sources of retinal images rather than stimulus features as such. Here we investigate the plausibility of this empirical concept of vision by allowing autonomous agents to evolve in virtual environments based solely on the relative success of their behavior. The responses of evolved agents to visual stimuli indicate that fitness improves as the neural network control systems gradually incorporate the statistical relationship between projected images and behavior appropriate to the sources of the inherently ambiguous images. These results: (1) demonstrate the merits of a wholly empirical strategy of animal vision as a means of contending with the inverse optics problem; (2) argue that the information incorporated into biological visual processing circuitry is the relationship between images and their probable sources; and (3) suggest why human percepts do not map neatly onto physical reality.

Full Text

Duke Authors

Cited Authors

  • Boots, B; Nundy, S; Purves, D

Published Date

  • March 2007

Published In

Volume / Issue

  • 18 / 1

Start / End Page

  • 11 - 34

PubMed ID

  • 17454680

International Standard Serial Number (ISSN)

  • 0954-898X

Digital Object Identifier (DOI)

  • 10.1080/09548980601113254

Language

  • eng

Conference Location

  • England