Dynamics of the evolution of learning algorithms by selection.

Full Abstract

We study the evolution of artificial learning systems by means of selection. Genetic programming is used to generate populations of programs that implement algorithms used by neural network classifiers to learn a rule in a supervised learning scenario. In contrast to concentrating on final results, which would be the natural aim while designing good learning algorithms, we study the evolution process. Phenotypic and genotypic entropies, which describe the distribution of fitness and of symbols, respectively, are used to monitor the dynamics. We identify significant functional structures responsible for the improvements in the learning process. In particular, some combinations of variables and operators are useful in assessing performance in rule extraction and can thus implement annealing of the learning schedule. We also find combinations that can signal surprise, measured on a single example, by the difference between predicted and correct classification. When such favorable structures appear, they are disseminated on very short time scales throughout the population. Due to such abruptness they can be thought of as dynamical transitions. But foremost, we find a strict temporal order of such discoveries. Structures that measure performance are never useful before those for measuring surprise. Invasions of the population by such structures in the reverse order were never observed. Asymptotically, the generalization ability approaches Bayesian results.

Learn Faster Today Improve your study skills

Author information

Author/s: Neirotti, Juan Pablo (JP); Caticha, Nestor (N);

Affiliation: Departamento de Física Geral, Instituto de Física, Universidade de São Paulo, Rua do Matão Travessa R 187, Brazil.

Journal and publication information

Publication Type: Journal Article

Journal: Physical review. E, Statistical, nonlinear, and soft matter physics (Phys Rev E Stat Nonlin Soft Matter Phys), published in United States. (Language: eng)

Reference: 2003-Apr; vol 67 (issue 4 Pt 1) : pp 041912

Dates: Created 2003/06/05; Completed 2003/09/26; Revised 2004/11/17;

PMID: 12786401, status: MEDLINE (last retrieval date: 11/6/2008)

Sourced from the National Library of Medicine. Abstract text and other information may be subject to copyright.

External Links for this article (including full text providers, if available):

Click Electronic Full-text Provider Links to see options for finding the electronic full text links to this article. Note there may be a subscription or fee required for access to the full text. See our FAQ for information on finding FREE full text articles.

This article may also be located in paper journal collections available in many libraries. Use the Journal and Publication Information above to find the full article.

MeSH headings (categories)

This article was linked to the MESH Headings shown below.

This article has not been indexed for related articles as yet, however you can still use the live related article search links below.

See 100+ related articles.