Slightly beyond Turing-Computability for studying Genetic Programming - Inria - Institut national de recherche en sciences et technologies du numérique
Communication Dans Un Congrès Année : 2007

Slightly beyond Turing-Computability for studying Genetic Programming

Olivier Teytaud

Résumé

Inspired by genetic programming (GP), we study iterative algorithms for non-computable tasks and compare them to naive models. This framework justifies many practical standard tricks from GP and also provides complexity lower-bounds which justify the computational cost of GP thanks to the use of Kolmogorov's complexity in bounded time.
Fichier principal
Vignette du fichier
essai.pdf (157.67 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00173241 , version 1 (19-09-2007)

Identifiants

  • HAL Id : inria-00173241 , version 1

Citer

Olivier Teytaud. Slightly beyond Turing-Computability for studying Genetic Programming. MCU'07, 2007, Orléans, France. ⟨inria-00173241⟩
143 Consultations
114 Téléchargements

Partager

More