Evolving a Learning Machine by Genetic Programming

Author

Alfaro-Cid, E. ; Sharman, K. ; Esparcia-Alcazar, A.I.

Author_Institution

Instituto Tecnológico de Informática, Universidad Politécnica de Valencia, Valencia, 46022, Spain (phone: +34 96 387 72 60; fax: +34 96 387 72 39; email: evalfaro@iti.upv.es)

fYear

0

fDate

0-0 0

Firstpage

254

Lastpage

258

Abstract

We describe a novel technique for evolving a machine that can learn. The machine is evolved using a Genetic Programming (GP) algorithm that incorporates in its function set what we have called a "learning node". Such a node is tuned by a second optimization algorithm (in this case Simulated Annealing), mimicking a natural learning process and providing the GP tree with added flexibility and adaptability. The result of the evolution is a system with a fixed structure but with some variable parameters. The system can then learn new tasks in new environments without undergoing further evolution.

Keywords

genetic algorithms; simulated annealing; function set; genetic programming; learning machine; learning node; optimization algorithm; simulated annealing; Animals; Capacity planning; Evolution (biology); Gain; Genetic programming; Machine learning; Simulated annealing; Stochastic processes; Terminology; Tree data structures;

fLanguage

English

Publisher

ieee

Conference_Titel

Evolutionary Computation, 2006. CEC 2006. IEEE Congress on

Conference_Location

Vancouver, BC

Print_ISBN

0-7803-9487-9

Type

conf

DOI

10.1109/CEC.2006.1688316

Filename

1688316