A bounded exploration approach to constructive algorithms for recurrent neural networks - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Neural Networks, IEEE - INNS - ENNS International Joint Conference on Année : 2000

A bounded exploration approach to constructive algorithms for recurrent neural networks

Résumé

When long-term dependencies are present in a time series, the approximation capabilities of recurrent neural networks are difficult to exploit by gradient descent algorithms. It is easier for such algorithms to find good solutions if one includes connections with time delays in the recurrent networks. One can choose the locations and delays for these connections by the heuristic presented here. As shown on two benchmark problems, this heuristic produces very good results while keeping the total number of connections in the recurrent network to a minimum.
Fichier principal
Vignette du fichier
ijcnn96.pdf (6.15 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01527874 , version 1 (25-05-2017)

Licence

Identifiants

  • HAL Id : hal-01527874 , version 1

Citer

Romuald Boné, Michel Crucianu, Gilles Verley, Jean-Pierre Asselin de Beauville. A bounded exploration approach to constructive algorithms for recurrent neural networks. Neural Networks, IEEE - INNS - ENNS International Joint Conference on, 2000. ⟨hal-01527874⟩
50 Consultations
50 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More