Spatial, temporal, and modulatory factors affecting the evolvability of GasNets - a style of artificial neural network incorporating an analogue of volume signalling - are investigated. The focus of the article is a comparative study of variants of the GasNet, implementing various spatial, temporal, and modulatory constraints, used as control systems in an evolutionary robotics task involving visual discrimination. The results of the study are discussed in the context of related research. © 2010 Wiley Periodicals, Inc.
- Evolutionary robotics
- Volume signalling