On the Locality of Neural Meta-representations

L.F. Simões, A.E. Eiben

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review


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.
Original languageEnglish
Title of host publicationProceedings of the 16th annual conference companion on Genetic and evolutionary computation
EditorsC. Igel
PublisherACM Press
ISBN (Print)9781450328814
Publication statusPublished - 2014
EventGenetic and Evolutionary Computation Conference (GECCO) -
Duration: 12 Jul 201416 Jul 2014


ConferenceGenetic and Evolutionary Computation Conference (GECCO)


Dive into the research topics of 'On the Locality of Neural Meta-representations'. Together they form a unique fingerprint.

Cite this