Slightly beyond Turing-Computability for studying Genetic Programming - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2007

Slightly beyond Turing-Computability for studying Genetic Programming

Olivier Teytaud

Abstract

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
Origin : Files produced by the author(s)
Loading...

Dates and versions

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

Identifiers

  • HAL Id : inria-00173241 , version 1

Cite

Olivier Teytaud. Slightly beyond Turing-Computability for studying Genetic Programming. MCU'07, 2007, Orléans, France. ⟨inria-00173241⟩
126 View
90 Download

Share

Gmail Facebook Twitter LinkedIn More