Skip to content

Evolving optimum camouflage with Generative Adversarial Networks

Research output: Contribution to journalArticle

Original languageEnglish
Article number429092
JournalbioRxiv
DOIs
DateSubmitted - 1 Oct 2018

Abstract

We describe a novel method to exploit Generative Adversarial Networks to simulate an evolutionary arms race between the camouflage of a synthetic prey and its predator. Patterns evolved using our methods are shown to provide progressively more effective concealment and outperform two recognised camouflage techniques. The method will be invaluable, particularly for biologists, for rapidly developing and testing optimal camouflage or signalling patterns in multiple environments.

Download statistics

No data available

Documents

Documents

  • 429092.full

    Submitted manuscript, 371 KB, PDF-document

    Licence: CC BY-NC-ND

DOI

View research connections

Related faculties, schools or groups