We consider the usage of artificial neural networks for representing genotype-phenotype maps, from and into continuous decision variable domains. Through such an approach, genetic representations become explicitly controllable entities, amenable to adaptation. With a view towards understanding the kinds of space transformations neural networks are able to express, we investigate here the typical representation locality given by arbitrary neuro-encoded genotypephenotype maps. We consistently find high locality space transformations being carried out, across all tested feedforward neural network architectures, in 5, 10 and 30 dimensional spaces.
|Title of host publication||Proceedings of the 16th annual conference companion on Genetic and evolutionary computation|
|Publication status||Published - 2014|
|Event||Genetic and Evolutionary Computation Conference (GECCO) - |
Duration: 12 Jul 2014 → 16 Jul 2014
|Conference||Genetic and Evolutionary Computation Conference (GECCO)|
|Period||12/07/14 → 16/07/14|