Genetic evolution of the topology and weight distribution of neural networks

Author

Maniezzo, Vittorio

Author_Institution

Dipartimento Elettronica e Informazzione, Politecnico di Milano, Italy

Volume

5

Issue

1

fYear

1994

fDate

1/1/1994 12:00:00 AM

Firstpage

39

Lastpage

53

Abstract

This paper proposes a system based on a parallel genetic algorithm with enhanced encoding and operational abilities. The system, used to evolve feedforward artificial neural networks, has been applied to two widely different problem areas: Boolean function learning and robot control. It is shown that the good results obtained in both cases are due to two factors: first, the enhanced exploration abilities provided by the search-space reducing evolution of both coding granularity and network topology, and, second, the enhanced exploitational abilities due to a recently proposed cooperative local optimizing genetic operator

Keywords

Boolean functions; feedforward neural nets; genetic algorithms; learning (artificial intelligence); network topology; parallel algorithms; robots; search problems; Boolean function learning; coding granularity; cooperative local optimizing genetic operator; exploitational abilities; exploration abilities; feedforward artificial neural networks; genetic evolution; neural networks; parallel genetic algorithm; robot control; search-space; topology; weight distribution; Algorithm design and analysis; Artificial neural networks; Backpropagation algorithms; Boolean functions; Computer networks; Encoding; Genetic algorithms; Network topology; Neural networks; Testing;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.265959

Filename

265959