Deterministic Nonmonotone Training: Recurrent Neural Networks and Applications using Symbolic Sequence Data - Couverture souple

Peng, Chun-Cheng

9783846599532: Deterministic Nonmonotone Training: Recurrent Neural Networks and Applications using Symbolic Sequence Data

Couverture souple

ISBN 10 : 3846599530 ISBN 13 : 9783846599532

Editeur : LAP Lambert Academic Publishing, 2011

Afficher les exemplaires de cette �dition comportant l?ISBN

1 D'occasion

De EUR 150,86

7 Neuf

De EUR 63,42

In this book, we propose novel deterministic RNN training algorithms that adopt a nonmonotone approach. This allows learning behaviour to deteriorate in some iterations; nevertheless the overall learning performance is improved over time. The nonmonotone RNN training methods, which take their theoretical basis from the theory of deterministic nonlinear optimisation, aim at better exploring the search space and enhancing the convergence behaviour of gradient-based methods. They generate nonmonotone behaviour by incorporating conditions that employ forcing functions, which are used to measure the sufficiency of error reduction, and an adaptive window, whose size is informed by estimating the morphology of the error surface locally. The thesis develops nonmonotone 1st- and 2nd-order methods and discusses their convergence properties. The proposed algorithms are applied to training RNNs of various sizes and architectures, namely Feed-Forward Time-Delay networks, Elman Networks and Nonlinear Autoregressive Networks with Exogenous Inputs Networks, in symbolic sequence processing problems. Numerical results show that the proposed nonmonotone learning algorithms train more effectively.

Les informations fournies dans la section � Synopsis � peuvent faire r�f�rence � une autre �dition de ce titre.

� propos de l?auteur

After granted his PhD (Neural Networks Learning) from the Computer Science and Information Systems Department of the Birkbeck College, University of London, England in 2011, Chun-Cheng Peng is currently a Post-doctoral Research Associate in National Chin-Yi University of Technology, Taiwan. His research interests are mainly in nonmonotone learning.

Les informations fournies dans la section � A propos du livre � peuvent faire r�f�rence � une autre �dition de ce titre.

�diteur: LAP Lambert Academic Publishing
Date d'�dition: 2011
Langue: anglais
ISBN 10: 3846599530
ISBN 13: 9783846599532
Reliure: Broch�
Nombre de pages: 256
Coordonn�es du fabricant: non disponible
Personne responsable: KreGa Onlinehandel GmbH
4950000000000
info@krega-onlinehandel.de

Birkenweg 31
Brakel
33034
Allemagne

Acheter D'occasion

�tat : Comme neuf

Like New

Afficher cet article

EUR 150,86

Autre devise

EUR 28,83 exp�dition depuis Royaume-Uni vers France

Destinations, frais et d�lais

Ajouter au panier

Acheter neuf

Afficher cet article

EUR 63,42

Autre devise

EUR 9,70 exp�dition depuis Allemagne vers France

Destinations, frais et d�lais

Ajouter au panier

R�sultats de recherche pour Deterministic Nonmonotone Training: Recurrent Neural...

Image fournie par le vendeur

Deterministic Nonmonotone Training

Chun-Cheng Peng

Edit� par LAP LAMBERT Academic Publishing, 2011

ISBN 10 : 3846599530 ISBN 13 : 9783846599532

Neuf Couverture souple

impression � la demande

Vendeur : moluna, Greven, Allemagne

�valuation du vendeur 5 sur 5 �toiles

Etat : New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. Autor/Autorin: Peng Chun-ChengAfter granted his PhD (Neural Networks Learning) from the Computer Science and Information Systems Department of the Birkbeck College, University of London, England in 2011, Chun-Cheng Peng is currently a Post-doctoral. N� de r�f. du vendeur 5502357

Contacter le vendeur

Acheter neuf

EUR 63,42

Autre devise

Frais de port : EUR 9,70

De Allemagne vers France

Destinations, frais et d�lais

Quantit� disponible : Plus de 20 disponibles

Ajouter au panier

Image fournie par le vendeur

Deterministic Nonmonotone Training : Recurrent Neural Networks and Applications using Symbolic Sequence Data

Chun-Cheng Peng

Edit� par LAP LAMBERT Academic Publishing, 2011

ISBN 10 : 3846599530 ISBN 13 : 9783846599532

Neuf Taschenbuch

impression � la demande

Vendeur : AHA-BUCH GmbH, Einbeck, Allemagne

�valuation du vendeur 5 sur 5 �toiles

Taschenbuch. Etat : Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - In this book, we propose novel deterministic RNN training algorithms that adopt a nonmonotone approach. This allows learning behaviour to deteriorate in some iterations; nevertheless the overall learning performance is improved over time. The nonmonotone RNN training methods, which take their theoretical basis from the theory of deterministic nonlinear optimisation, aim at better exploring the search space and enhancing the convergence behaviour of gradient-based methods. They generate nonmonotone behaviour by incorporating conditions that employ forcing functions, which are used to measure the sufficiency of error reduction, and an adaptive window, whose size is informed by estimating the morphology of the error surface locally. The thesis develops nonmonotone 1st- and 2nd-order methods and discusses their convergence properties. The proposed algorithms are applied to training RNNs of various sizes and architectures, namely Feed-Forward Time-Delay networks, Elman Networks and Nonlinear Autoregressive Networks with Exogenous Inputs Networks, in symbolic sequence processing problems. Numerical results show that the proposed nonmonotone learning algorithms train more effectively. N� de r�f. du vendeur 9783846599532

Contacter le vendeur

Acheter neuf

EUR 79

Autre devise

Frais de port : EUR 10,99

De Allemagne vers France

Destinations, frais et d�lais

Quantit� disponible : 1 disponible(s)

Ajouter au panier

Image fournie par le vendeur

Deterministic Nonmonotone Training

Chun-Cheng Peng

Edit� par LAP LAMBERT Academic Publishing Nov 2011, 2011

ISBN 10 : 3846599530 ISBN 13 : 9783846599532

Neuf Taschenbuch

impression � la demande

Vendeur : BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Allemagne

�valuation du vendeur 5 sur 5 �toiles

Taschenbuch. Etat : Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -In this book, we propose novel deterministic RNN training algorithms that adopt a nonmonotone approach. This allows learning behaviour to deteriorate in some iterations; nevertheless the overall learning performance is improved over time. The nonmonotone RNN training methods, which take their theoretical basis from the theory of deterministic nonlinear optimisation, aim at better exploring the search space and enhancing the convergence behaviour of gradient-based methods. They generate nonmonotone behaviour by incorporating conditions that employ forcing functions, which are used to measure the sufficiency of error reduction, and an adaptive window, whose size is informed by estimating the morphology of the error surface locally. The thesis develops nonmonotone 1st- and 2nd-order methods and discusses their convergence properties. The proposed algorithms are applied to training RNNs of various sizes and architectures, namely Feed-Forward Time-Delay networks, Elman Networks and Nonlinear Autoregressive Networks with Exogenous Inputs Networks, in symbolic sequence processing problems. Numerical results show that the proposed nonmonotone learning algorithms train more effectively. 256 pp. Englisch. N� de r�f. du vendeur 9783846599532

Contacter le vendeur

Acheter neuf

EUR 79

Autre devise

Frais de port : EUR 11

De Allemagne vers France

Destinations, frais et d�lais

Quantit� disponible : 2 disponible(s)

Ajouter au panier

Image fournie par le vendeur

Deterministic Nonmonotone Training

Chun-Cheng Peng

Edit� par LAP LAMBERT Academic Publishing Nov 2011, 2011

ISBN 10 : 3846599530 ISBN 13 : 9783846599532

Neuf Taschenbuch

Vendeur : buchversandmimpf2000, Emtmannsberg, BAYE, Allemagne

�valuation du vendeur 5 sur 5 �toiles

Taschenbuch. Etat : Neu. Neuware -In this book, we propose novel deterministic RNN training algorithms that adopt a nonmonotone approach. This allows learning behaviour to deteriorate in some iterations; nevertheless the overall learning performance is improved over time. The nonmonotone RNN training methods, which take their theoretical basis from the theory of deterministic nonlinear optimisation, aim at better exploring the search space and enhancing the convergence behaviour of gradient-based methods. They generate nonmonotone behaviour by incorporating conditions that employ forcing functions, which are used to measure the sufficiency of error reduction, and an adaptive window, whose size is informed by estimating the morphology of the error surface locally. The thesis develops nonmonotone 1st- and 2nd-order methods and discusses their convergence properties. The proposed algorithms are applied to training RNNs of various sizes and architectures, namely Feed-Forward Time-Delay networks, Elman Networks and Nonlinear Autoregressive Networks with Exogenous Inputs Networks, in symbolic sequence processing problems. Numerical results show that the proposed nonmonotone learning algorithms train more effectively.Books on Demand GmbH, �berseering 33, 22297 Hamburg 256 pp. Englisch. N� de r�f. du vendeur 9783846599532

Contacter le vendeur