Modular thinking

Ehud Schlessinger, Peter J. Bentley, R. Beau Lotto
2006 Proceedings of the 8th annual conference on Genetic and evolutionary computation - GECCO '06  
This paper investigates whether replacing non-modular artificial neural network brains of visual agents with modular brains improves their ability to solve difficult tasks, specifically, survive in a changing environment. A set of experiments was conducted and confirmed that agents with modular brains are in fact better. Further analysis of the evolved modules characterised their function and determined their mechanism of operation. The results indicate that the greater survival ability is
more » ... ned due to functional specialisation of the evolved modules; good agents do well because their modules are more specialised at tasks such as reproduction and consumption. Overall, the more specialised the modules, the fitter the agents.
doi:10.1145/1143997.1144033 dblp:conf/gecco/SchlessingerBL06 fatcat:qj66rkdr7nc4dpi2o5g772mmzi