The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
La conception de réseaux de neurones artificiels (ANN) grâce à une évolution simulée est étudiée depuis de nombreuses années. L'utilisation d'algorithmes génétiques (AG) pour une telle évolution souffre d'un problème important connu sous le nom de problème de permutation ou problème de convention concurrente. Cet article propose un nouvel opérateur de croisement, que nous appelons le croisement de nœuds sélectionnés (SNX), pour surmonter le problème de permutation des GA pour les ANN en évolution. L'invention concerne un système évolutif basé sur GA (GANet) utilisant le SNX pour faire évoluer une architecture ANN à rétroaction à trois couches avec apprentissage de poids. GANet utilise séquentiellement un opérateur de croisement et un opérateur de mutation. Si le premier opérateur réussit, le deuxième opérateur n'est pas appliqué. GANet dépend moins des paramètres de contrôle définis par l'utilisateur que les méthodes évolutives conventionnelles. GANet est appliqué à une variété de tests de référence, y compris les problèmes de classification de grande taille (26 classes) à petits (2 classes). Les résultats montrent que GANet peut produire des architectures ANN compactes avec de petites erreurs de classification.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Md. Monirul ISLAM, Kazuyuki MURASE, "A New Crossover Operator and Its Application to Artificial Neural Networks Evolution" in IEICE TRANSACTIONS on Information,
vol. E84-D, no. 9, pp. 1144-1154, September 2001, doi: .
Abstract: The design of artificial neural networks (ANNs) through simulated evolution has been investigated for many years. The use of genetic algorithms (GAs) for such evolution suffers a prominent problem known as the permutation problem or the competing convention problem. This paper proposes a new crossover operator, which we call the selected node crossover (SNX), to overcome the permutation problem of GAs for evolving ANNs. A GA-based evolutionary system (GANet) using the SNX for evolving three layered feedforward ANNs architecture with weight learning is described. GANet uses one crossover and one mutation operators sequentially. If the first operator is successful then the second operator is not applied. GANet is less dependent on user-defined control parameters than the conventional evolutionary methods. GANet is applied to a variety of benchmarks including large (26 class) to small (2 class) classification problems. The results show that GANet can produce compact ANN architectures with small classification errors.
URL: https://global.ieice.org/en_transactions/information/10.1587/e84-d_9_1144/_p
Copier
@ARTICLE{e84-d_9_1144,
author={Md. Monirul ISLAM, Kazuyuki MURASE, },
journal={IEICE TRANSACTIONS on Information},
title={A New Crossover Operator and Its Application to Artificial Neural Networks Evolution},
year={2001},
volume={E84-D},
number={9},
pages={1144-1154},
abstract={The design of artificial neural networks (ANNs) through simulated evolution has been investigated for many years. The use of genetic algorithms (GAs) for such evolution suffers a prominent problem known as the permutation problem or the competing convention problem. This paper proposes a new crossover operator, which we call the selected node crossover (SNX), to overcome the permutation problem of GAs for evolving ANNs. A GA-based evolutionary system (GANet) using the SNX for evolving three layered feedforward ANNs architecture with weight learning is described. GANet uses one crossover and one mutation operators sequentially. If the first operator is successful then the second operator is not applied. GANet is less dependent on user-defined control parameters than the conventional evolutionary methods. GANet is applied to a variety of benchmarks including large (26 class) to small (2 class) classification problems. The results show that GANet can produce compact ANN architectures with small classification errors.},
keywords={},
doi={},
ISSN={},
month={September},}
Copier
TY - JOUR
TI - A New Crossover Operator and Its Application to Artificial Neural Networks Evolution
T2 - IEICE TRANSACTIONS on Information
SP - 1144
EP - 1154
AU - Md. Monirul ISLAM
AU - Kazuyuki MURASE
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E84-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2001
AB - The design of artificial neural networks (ANNs) through simulated evolution has been investigated for many years. The use of genetic algorithms (GAs) for such evolution suffers a prominent problem known as the permutation problem or the competing convention problem. This paper proposes a new crossover operator, which we call the selected node crossover (SNX), to overcome the permutation problem of GAs for evolving ANNs. A GA-based evolutionary system (GANet) using the SNX for evolving three layered feedforward ANNs architecture with weight learning is described. GANet uses one crossover and one mutation operators sequentially. If the first operator is successful then the second operator is not applied. GANet is less dependent on user-defined control parameters than the conventional evolutionary methods. GANet is applied to a variety of benchmarks including large (26 class) to small (2 class) classification problems. The results show that GANet can produce compact ANN architectures with small classification errors.
ER -