Slightly beyond Turing's computability for studying genetic programming

  • Authors:
  • Olivier Teytaud

  • Affiliations:
  • TAO, INRIA Futurs, LRI, UMR, CNRS, Univ. Paris-Sud

  • Venue:
  • MCU'07 Proceedings of the 5th international conference on Machines, computations, and universality
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

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 Kolmogorovs complexity in bounded time.