Sinossi
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.
Le informazioni nella sezione "Riassunto" possono far riferimento a edizioni diverse di questo titolo.
Contenuti
Recurrent and folding networks.- Approximation ability.- Learnability.- Complexity.- Conclusion.
Product Description
Book by Hammer Barbara
Le informazioni nella sezione "Su questo libro" possono far riferimento a edizioni diverse di questo titolo.
Altre edizioni note dello stesso titolo
Risultati della ricerca per Learning with Recurrent Neural Networks: 254
Foto dell'editore
Learnng With Recurrent Neural Networks
Da: Basi6 International, Irving, TX, U.S.A.
Valutazione del venditore 5 su 5 stelle
Condizione: Brand New. New. US edition. Expediting shipping for all USA and Europe orders excluding PO Box. Excellent Customer Service. Codice articolo ABEOCT25-223373
Compra nuovo
EUR 47,49
Spedizione gratuita
Spedito in U.S.A.
Spedito in U.S.A.
Quantità: 1 disponibili
Foto dell'editore
Learning with Recurrent Neural Networks
Da: Books Puddle, New York, NY, U.S.A.
Valutazione del venditore 4 su 5 stelle
Condizione: New. pp. 164. Codice articolo 263077656
Compra nuovo
EUR 71,07
Spedizione EUR 3,44
Spedito in U.S.A.
Spedito in U.S.A.
Quantità: 4 disponibili
Immagini fornite dal venditore
Learning with Recurrent Neural Networks.
Editore:
London, Springer London Limited, 2000
ISBN 10: 185233343X
ISBN 13: 9781852333430
Antico o usato
Softcover
Da: Antiquariat Bookfarm, Löbnitz, Germania
Valutazione del venditore 5 su 5 stelle
Softcover. 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. Codice articolo 2341525
Compra usato
EUR 38,40
Spedizione EUR 40,00
Spedito da Germania a U.S.A.
Spedito da Germania a U.S.A.
Quantità: 1 disponibili
Foto dell'editore
Learning with Recurrent Neural Networks
Print on DemandDa: Majestic Books, Hounslow, Regno Unito
Valutazione del venditore 4 su 5 stelle
Condizione: New. Print on Demand pp. 164 Illus. Codice articolo 5851591
Compra nuovo
EUR 75,12
Spedizione EUR 7,53
Spedito da Regno Unito a U.S.A.
Spedito da Regno Unito a U.S.A.
Quantità: 4 disponibili
Foto dell'editore
Learning with Recurrent Neural Networks
Print on DemandDa: Biblios, Frankfurt am main, HESSE, Germania
Valutazione del venditore 4 su 5 stelle
Condizione: New. PRINT ON DEMAND pp. 164. Codice articolo 183077650
Compra nuovo
EUR 75,95
Spedizione EUR 9,95
Spedito da Germania a U.S.A.
Spedito da Germania a U.S.A.
Quantità: 4 disponibili
Immagini fornite dal venditore
Learning with Recurrent Neural Networks
Print on DemandDa: moluna, Greven, Germania
Valutazione del venditore 5 su 5 stelle
Condizione: 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 . Codice articolo 4289491
Compra nuovo
EUR 48,37
Spedizione EUR 48,99
Spedito da Germania a U.S.A.
Spedito da Germania a U.S.A.
Quantità: Più di 20 disponibili
Immagini fornite dal venditore
Learning with Recurrent Neural Networks
Editore:
Springer, Springer Mai 2000, 2000
ISBN 10: 185233343X
ISBN 13: 9781852333430
Nuovo
Taschenbuch
Da: buchversandmimpf2000, Emtmannsberg, BAYE, Germania
Valutazione del venditore 5 su 5 stelle
Taschenbuch. Condizione: 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 KG, Sachsenplatz 4-6, 1201 Wien 164 pp. Englisch. Codice articolo 9781852333430
Compra nuovo
EUR 53,49
Spedizione EUR 60,00
Spedito da Germania a U.S.A.
Spedito da Germania a U.S.A.
Quantità: 1 disponibili
Immagini fornite dal venditore
Learning with Recurrent Neural Networks
Da: AHA-BUCH GmbH, Einbeck, Germania
Valutazione del venditore 5 su 5 stelle
Taschenbuch. Condizione: 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. Codice articolo 9781852333430
Compra nuovo
EUR 58,39
Spedizione EUR 61,29
Spedito da Germania a U.S.A.
Spedito da Germania a U.S.A.
Quantità: 1 disponibili
Immagini fornite dal venditore
Learning with Recurrent Neural Networks
Da: preigu, Osnabrück, Germania
Valutazione del venditore 5 su 5 stelle
Taschenbuch. Condizione: Neu. Learning with Recurrent Neural Networks | Barbara Hammer | Taschenbuch | 150 S. | Englisch | 2000 | Springer | EAN 9781852333430 | Verantwortliche Person für die EU: Springer Verlag GmbH, Tiergartenstr. 17, 69121 Heidelberg, juergen[dot]hartmann[at]springer[dot]com | Anbieter: preigu. Codice articolo 105808074
Compra nuovo
EUR 50,25
Spedizione EUR 70,00
Spedito da Germania a U.S.A.
Spedito da Germania a U.S.A.
Quantità: 5 disponibili
Immagini fornite dal venditore
Learning with Recurrent Neural Networks
Da: Buchpark, Trebbin, Germania
Valutazione del venditore 5 su 5 stelle
Condizione: Sehr gut. Zustand: Sehr gut | Sprache: Englisch | Produktart: Bücher | 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. Codice articolo 365584/2
Compra usato
EUR 37,89
Spedizione EUR 105,00
Spedito da Germania a U.S.A.
Spedito da Germania a U.S.A.
Quantità: 1 disponibili