|
Abstract:
|
In order for neuroevolutionary techniques to produce increasingly complex and sophisticated topologies, new methods need to be developed which effectively exploit reuse and modularity. Bilateral symmetry is an important form of reuse and a key feature of complex biological central nervous systems. We present a method for encoding bilateral symmetry within the context of an existing neuroevolutionary framework, NEAT (NeuroEvolution of Augmenting Topologies). We then present a model of symmetry detection that relies on the symmetry in the structure of the neural system to make symmetry judgments. We demonstrate that this model performs better than an asymmetrical representation on a symmetry discrimination task in which the axis of symmetry is given. On a second task, the networks must first find the axis of symmetry before making the symmetry judgment. In this task the symmetrical encoding performs worse than the asymmetrical one. We discuss some possible explanations for these results.
|
