Zustand: Sehr gut. Zustand: Sehr gut | Sprache: Englisch | Produktart: Bücher.
Verlag: London, Springer London Limited, 2000
ISBN 10: 185233343X ISBN 13: 9781852333430
Sprache: Englisch
Anbieter: Antiquariat Bookfarm, Löbnitz, Deutschland
EUR 38,40
Währung umrechnenAnzahl: 1 verfügbar
In den WarenkorbSoftcover. 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.
Anbieter: ALLBOOKS1, Direk, SA, Australien
EUR 49,40
Währung umrechnenAnzahl: 1 verfügbar
In den Warenkorb
EUR 58,39
Währung umrechnenAnzahl: 1 verfügbar
In den WarenkorbTaschenbuch. Zustand: 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.
Anbieter: Ria Christie Collections, Uxbridge, Vereinigtes Königreich
EUR 60,32
Währung umrechnenAnzahl: Mehr als 20 verfügbar
In den WarenkorbZustand: New. In.
EUR 53,01
Währung umrechnenAnzahl: Mehr als 20 verfügbar
In den WarenkorbZustand: New.
EUR 56,34
Währung umrechnenAnzahl: 10 verfügbar
In den WarenkorbPF. Zustand: New.
Anbieter: Best Price, Torrance, CA, USA
EUR 48,33
Währung umrechnenAnzahl: 1 verfügbar
In den WarenkorbZustand: New. SUPER FAST SHIPPING.
Anbieter: GreatBookPricesUK, Woodford Green, Vereinigtes Königreich
EUR 59,29
Währung umrechnenAnzahl: Mehr als 20 verfügbar
In den WarenkorbZustand: New.
EUR 60,54
Währung umrechnenAnzahl: Mehr als 20 verfügbar
In den WarenkorbZustand: As New. Unread book in perfect condition.
EUR 74,14
Währung umrechnenAnzahl: 4 verfügbar
In den WarenkorbZustand: New. pp. 164.
Anbieter: GreatBookPricesUK, Woodford Green, Vereinigtes Königreich
EUR 66,05
Währung umrechnenAnzahl: Mehr als 20 verfügbar
In den WarenkorbZustand: As New. Unread book in perfect condition.
Anbieter: Lucky's Textbooks, Dallas, TX, USA
EUR 51,99
Währung umrechnenAnzahl: Mehr als 20 verfügbar
In den WarenkorbZustand: New.
Anbieter: moluna, Greven, Deutschland
EUR 48,37
Währung umrechnenAnzahl: Mehr als 20 verfügbar
In den WarenkorbZustand: 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 .
Verlag: Springer London, Springer London Mai 2000, 2000
ISBN 10: 185233343X ISBN 13: 9781852333430
Sprache: Englisch
Anbieter: buchversandmimpf2000, Emtmannsberg, BAYE, Deutschland
EUR 53,49
Währung umrechnenAnzahl: 1 verfügbar
In den WarenkorbTaschenbuch. Zustand: 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.
Anbieter: THE SAINT BOOKSTORE, Southport, Vereinigtes Königreich
EUR 67,53
Währung umrechnenAnzahl: Mehr als 20 verfügbar
In den WarenkorbPaperback / softback. Zustand: New. This item is printed on demand. New copy - Usually dispatched within 5-9 working days 560.
Anbieter: Biblios, Frankfurt am main, HESSE, Deutschland
EUR 78,79
Währung umrechnenAnzahl: 4 verfügbar
In den WarenkorbZustand: New. PRINT ON DEMAND pp. 164.
Anbieter: Majestic Books, Hounslow, Vereinigtes Königreich
EUR 75,81
Währung umrechnenAnzahl: 4 verfügbar
In den WarenkorbZustand: New. Print on Demand pp. 164 Illus.
Anbieter: BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Deutschland
EUR 123,04
Währung umrechnenAnzahl: 2 verfügbar
In den WarenkorbTaschenbuch. Zustand: 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.