Phylogenetically Acquired Representations and Evolutionary Algorithms. - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2006

Phylogenetically Acquired Representations and Evolutionary Algorithms.

Adrianna Wozniak
  • Fonction : Auteur
  • PersonId : 835093

Résumé

First, we explain why Genetic Algorithms (GAs), inspired by the Modern Synthesis, do not accurately model biological evolution, being rather an artificial version of artificial, rather than natural selection. Being focused on optimisation, we propose two improvements of GAs, with the aim to successfully generate adapted, desired behaviour. The first one concerns phylogenetic grounding of meaning, a way to avoid the Symbol Grounding Problem. We give a definition of Phylogenetically Acquired Representations, based on a parallel between the notions of representation and of adaptation. In the second part of the paper, we propose a hybrid version of genetic algorithms, differently organizing the flow of genetic information by introducing inheritance of acquired traits and Horizontal Gene Transfer, a good tool for handle a cumulative directional process of artificial selection.
Fichier principal
Vignette du fichier
Laval.pdf (75.6 Ko) Télécharger le fichier

Dates et versions

hal-00095278 , version 1 (15-09-2006)
hal-00095278 , version 2 (16-09-2006)

Identifiants

  • HAL Id : hal-00095278 , version 1

Citer

Adrianna Wozniak. Phylogenetically Acquired Representations and Evolutionary Algorithms.. Computers and Philosophy, 2006, Laval, France. ⟨hal-00095278v1⟩

Collections

ISC
112 Consultations
118 Téléchargements

Partager

Gmail Facebook X LinkedIn More