Artificial Neuron–Glia Networks Learning Approach Based on Cooperative Coevolution

Abstract : Artificial Neuron-Glia Networks (ANGNs) are a novel bio-inspired machine learning approach. They extend classical Artificial Neural Networks (ANNs) by incorporating recent findings and suppositions about the way information is processed by neural and astrocytic networks in the most evolved living organisms. Although ANGNs are not a consolidated method, their performance against the traditional approach, i.e. without artificial astrocytes, was already demonstrated on classification problems. However , the corresponding learning algorithms developed so far strongly depends on a set of glial parameters which are manually tuned for each specific problem. As a consequence, previous experimental tests have to be done in order to determine an adequate set of values, making such manual parameter configuration time-consuming, error-prone, biased and problem dependent. Thus, in this article, we propose a novel learning approach for ANGNs that fully automates the learning process, and gives the possibility of testing any kind of reasonable parameter configuration for each specific problem. This new learning algorithm, based on coevolutionary genetic algorithms, is able to properly learn all the ANGNs parameters. Its performance is tested on 5 classification problems achieving significantly better results than ANGN and competitive results with ANN approaches.
Type de document :
Article dans une revue
International Journal of Neural Systems, World Scientific Publishing, 2015, 25 (4), 〈10.1142/S0129065715500124〉
Liste complète des métadonnées

Littérature citée [72 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01221226
Contributeur : Pablo Mesejo Santiago <>
Soumis le : mercredi 28 octobre 2015 - 11:47:15
Dernière modification le : jeudi 11 janvier 2018 - 06:23:32
Document(s) archivé(s) le : vendredi 29 janvier 2016 - 13:10:07

Fichier

paperReviewed2.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Pablo Mesejo, Óscar Ibáñez, Enrique Fernández-Blanco, Francisco Cedrón, Alejandro Pazos, et al.. Artificial Neuron–Glia Networks Learning Approach Based on Cooperative Coevolution. International Journal of Neural Systems, World Scientific Publishing, 2015, 25 (4), 〈10.1142/S0129065715500124〉. 〈hal-01221226〉

Partager

Métriques

Consultations de la notice

102

Téléchargements de fichiers

270