Too Busy to Learn

Authors

Francisco Baptista Pereira
Penousal Machado
Ernesto Costa
F. Amilcar Cardoso
Alberto Ochoa-Rodriguez
Roberto Santana
Marta Soto

Abstract

The goal of this research is to analyze how individual learning interacts with an evolutionary algorithm in its search for best candidates for the Busy Beaver problem. To study this interaction two learning models, implemented as local search procedures, are proposed. Experimental results show that, in highly irregular and prone to premature convergence search spaces, local search methods are not an effective help to evolution. In addition, one interesting effect related to learning is reported. When the mutation rate is too high, learning acts as a repair, reintroducing some useful information that was lost.

PDF File

Cited by

Year 2015 : 1 citations

Forced evolution in silico by artificial transposons and their genetic operators: The ant navigation problem
L Zamdborg, DM Holloway, JJ Merelo, VF Levchenko… - Information …, 2015 - Elsevier

Year 2011 : 1 citations

Spirov, Alexander V., et al. "FORCED EVOLUTION IN SILICO BY ARTIFICIAL TRANSPOSONS AND THEIR GENETIC OPERATORS: THE ANT NAVIGATION PROBLEM." 2011.

Year 2009 : 2 citations

C. Lima (2009). Substructural Local Search in Discrete Estimation of Distribution Algorithms. Ph.D. Thesis, Universidade do Algarve.

**Spirov, Alexander V., et al. "Forced evolution in silico by artificial transposons and their genetic operators: the john muir ant problem." arXiv preprint arXiv:0910.5542 (2009).

Year 2002 : 1 citations

Nattee Niparnan, A Genetic Algorithm for Finite State Machine
Inference, PhD Thesis, Chulalongkorn University, 2002.