Edité par London, Springer London Limited, 2000
ISBN 10 : 185233343X ISBN 13 : 9781852333430
Langue: anglais
Vendeur : Antiquariat Bookfarm, Löbnitz, Allemagne
EUR 38,40
Autre deviseQuantité disponible : 1 disponible(s)
Ajouter au panierSoftcover. 155 S. Ehem. Bibliotheksexemplar mit Signatur und Stempel. GUTER Zustand, ein paar Gebrauchsspuren. Ex-library with stamp and library-signature. GOOD condition, some traces of use. 9781852333430 Sprache: Englisch Gewicht in Gramm: 550.
EUR 39,46
Autre deviseQuantité disponible : 1 disponible(s)
Ajouter au panierEtat : Sehr gut. Zustand: Sehr gut | Seiten: 164 | Sprache: Englisch | Produktart: Sonstiges.
Vendeur : Ria Christie Collections, Uxbridge, Royaume-Uni
EUR 60,52
Autre deviseQuantité disponible : Plus de 20 disponibles
Ajouter au panierEtat : New. In.
EUR 56,53
Autre deviseQuantité disponible : 10 disponible(s)
Ajouter au panierPF. Etat : New.
EUR 54,56
Autre deviseQuantité disponible : Plus de 20 disponibles
Ajouter au panierEtat : New.
EUR 58,39
Autre deviseQuantité disponible : 1 disponible(s)
Ajouter au panierTaschenbuch. Etat : Neu. Druck auf Anfrage Neuware - Printed after ordering - Folding networks, a generalisation of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on classical symbolic data, for example. The architecture, the training mechanism, and several applications in different areas are explained. Afterwards a theoretical foundation, proving that the approach is appropriate as a learning mechanism in principle, is presented: Their universal approximation ability is investigated - including several new results for standard recurrent neural networks such as explicit bounds on the required number of neurons and the super Turing capability of sigmoidal recurrent networks. The information theoretical learnability is examined - including several contribution to distribution dependent learnability, an answer to an open question posed by Vidyasagar, and a generalisation of the recent luckiness framework to function classes. Final ly, the complexity of training is considered - including new results on the loading problem for standard feedforward networks with an arbitrary multilayered architecture, a correlated number of neurons and training set size, a varying number of hidden neurons but fixed input dimension, or the sigmoidal activation function, respectively.
EUR 59,49
Autre deviseQuantité disponible : Plus de 20 disponibles
Ajouter au panierEtat : New.
EUR 62,12
Autre deviseQuantité disponible : Plus de 20 disponibles
Ajouter au panierEtat : As New. Unread book in perfect condition.
EUR 66,38
Autre deviseQuantité disponible : Plus de 20 disponibles
Ajouter au panierEtat : As New. Unread book in perfect condition.
EUR 76,64
Autre deviseQuantité disponible : 4 disponible(s)
Ajouter au panierEtat : New. pp. 164.
Vendeur : Lucky's Textbooks, Dallas, TX, Etats-Unis
EUR 53,34
Autre deviseQuantité disponible : Plus de 20 disponibles
Ajouter au panierEtat : New.
Vendeur : moluna, Greven, Allemagne
EUR 48,37
Autre deviseQuantité disponible : Plus de 20 disponibles
Ajouter au panierEtat : New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. The book details a new approach which enables neural networks to deal with symbolic data, folding networksIt presents both practical applications and a precise theoretical foundationFolding networks, a generalisation of recurrent neural networks to .
Edité par Springer London, Springer London Mai 2000, 2000
ISBN 10 : 185233343X ISBN 13 : 9781852333430
Langue: anglais
Vendeur : buchversandmimpf2000, Emtmannsberg, BAYE, Allemagne
EUR 53,49
Autre deviseQuantité disponible : 1 disponible(s)
Ajouter au panierTaschenbuch. Etat : Neu. This item is printed on demand - Print on Demand Titel. Neuware -Folding networks, a generalisation of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on classical symbolic data, for example. The architecture, the training mechanism, and several applications in different areas are explained. Afterwards a theoretical foundation, proving that the approach is appropriate as a learning mechanism in principle, is presented: Their universal approximation ability is investigated- including several new results for standard recurrent neural networks such as explicit bounds on the required number of neurons and the super Turing capability of sigmoidal recurrent networks. The information theoretical learnability is examined - including several contribution to distribution dependent learnability, an answer to an open question posed by Vidyasagar, and a generalisation of the recent luckiness framework to function classes. Finally, the complexity of training is considered - including new results on the loading problem for standard feedforward networks with an arbitrary multilayered architecture, a correlated number of neurons and training set size, a varying number of hidden neurons but fixed input dimension, or the sigmoidal activation function, respectively.Springer Verlag GmbH, Tiergartenstr. 17, 69121 Heidelberg 164 pp. Englisch.
Vendeur : THE SAINT BOOKSTORE, Southport, Royaume-Uni
EUR 66,80
Autre deviseQuantité disponible : Plus de 20 disponibles
Ajouter au panierPaperback / softback. Etat : New. This item is printed on demand. New copy - Usually dispatched within 5-9 working days 560.
Vendeur : Majestic Books, Hounslow, Royaume-Uni
EUR 79,41
Autre deviseQuantité disponible : 4 disponible(s)
Ajouter au panierEtat : New. Print on Demand pp. 164 Illus.
Vendeur : Biblios, Frankfurt am main, HESSE, Allemagne
EUR 80,39
Autre deviseQuantité disponible : 4 disponible(s)
Ajouter au panierEtat : New. PRINT ON DEMAND pp. 164.
Edité par Springer London Mai 2000, 2000
ISBN 10 : 185233343X ISBN 13 : 9781852333430
Langue: anglais
Vendeur : BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Allemagne
EUR 123,04
Autre deviseQuantité disponible : 2 disponible(s)
Ajouter au panierTaschenbuch. Etat : Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -Folding networks, a generalisation of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on classical symbolic data, for example. The architecture, the training mechanism, and several applications in different areas are explained. Afterwards a theoretical foundation, proving that the approach is appropriate as a learning mechanism in principle, is presented: Their universal approximation ability is investigated - including several new results for standard recurrent neural networks such as explicit bounds on the required number of neurons and the super Turing capability of sigmoidal recurrent networks. The information theoretical learnability is examined - including several contribution to distribution dependent learnability, an answer to an open question posed by Vidyasagar, and a generalisation of the recent luckiness framework to function classes. Final ly, the complexity of training is considered - including new results on the loading problem for standard feedforward networks with an arbitrary multilayered architecture, a correlated number of neurons and training set size, a varying number of hidden neurons but fixed input dimension, or the sigmoidal activation function, respectively. 164 pp. Englisch.