RT Journal Article
SR Electronic
T1 Evolving optimum camouflage with Generative Adversarial Networks
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 429092
DO 10.1101/429092
A1 Laszlo Tala
A1 John G. Fennell
A1 Karin Kjernsmo
A1 Innes C. Cuthill
A1 Nicholas E. Scott-Samuel
A1 Roland J. Baddeley
YR 2018
UL http://biorxiv.org/content/early/2018/09/29/429092.abstract
AB 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.