4#1

Temporally Adaptive Networks: Analysis of GasNet Robot Control Networks

Tom Smith $^{*\ddag }$, Phil Husbands$^\dag$, Andy Philippides^* and Michael O'Shea^*

Centre for Computational Neuroscience and Robotics (CCNR)
^*School of Biological Sciences, $^\dag$School of Cognitive and Computing Sciences
University of Sussex, Brighton, UK.
Email: toms@cogs.susx.ac.uk. Web: http://www.cogs.susx.ac.uk/users/toms/

   

Abstract:

Identification of the fundamental properties necessary for the generation of adaptive behaviour is one of the primary goals for Artificial Life. In this paper, we address the related question of whether we can identify general useful properties of a given solution class. Such an approach provides a potentially scalable framework that may enable us to identify general properties of more complex adaptive systems.  We develop a methodology based on analysis of successfully evolved solutions to an evolutionary robotics shape discrimination problem, allowing us to identify properties of solution classes that are potentially useful over a wider class of problems than the original task. We propose that the evolvability of the solution class is due to the fundamental property of temporal adaptivity.