Editore: London ; Berlin ; Tokyo ; Heidelberg ; New York ; Barcelona ; Hong Kong ; Milan ; Paris ; Santa Clara ; Singapore : Springer, 1999
ISBN 10: 1852330953 ISBN 13: 9781852330958
Lingua: Inglese
Da: Roland Antiquariat UG haftungsbeschränkt, Weinheim, Germania
EUR 56,00
Convertire valutaQuantità: 1 disponibili
Aggiungi al carrelloSoftcover. XXIII, 275 S. : graph. Darst. ; 24 cm Like new. Unread book. --- Neuwertiger Zustand. Ungelesenes Buch. 9781852330958 Sprache: Deutsch Gewicht in Gramm: 467 Softcover reprint of the original 1st ed. 1999.
Da: Ria Christie Collections, Uxbridge, Regno Unito
EUR 62,09
Convertire valutaQuantità: Più di 20 disponibili
Aggiungi al carrelloCondizione: New. In.
Da: California Books, Miami, FL, U.S.A.
EUR 66,70
Convertire valutaQuantità: Più di 20 disponibili
Aggiungi al carrelloCondizione: New.
Da: AHA-BUCH GmbH, Einbeck, Germania
EUR 59,97
Convertire valutaQuantità: 1 disponibili
Aggiungi al carrelloTaschenbuch. Condizione: Neu. Druck auf Anfrage Neuware - Printed after ordering - Conventional applications of neural networks usually predict a single value as a function of given inputs. In forecasting, for example, a standard objective is to predict the future value of some entity of interest on the basis of a time series of past measurements or observations. Typical training schemes aim to minimise the sum of squared deviations between predicted and actual values (the 'targets'), by which, ideally, the network learns the conditional mean of the target given the input. If the underlying conditional distribution is Gaus sian or at least unimodal, this may be a satisfactory approach. However, for a multimodal distribution, the conditional mean does not capture the relevant features of the system, and the prediction performance will, in general, be very poor. This calls for a more powerful and sophisticated model, which can learn the whole conditional probability distribution. Chapter 1 demonstrates that even for a deterministic system and 'be nign' Gaussian observational noise, the conditional distribution of a future observation, conditional on a set of past observations, can become strongly skewed and multimodal. In Chapter 2, a general neural network structure for modelling conditional probability densities is derived, and it is shown that a universal approximator for this extended task requires at least two hidden layers. A training scheme is developed from a maximum likelihood approach in Chapter 3, and the performance ofthis method is demonstrated on three stochastic time series in chapters 4 and 5.
Da: Chiron Media, Wallingford, Regno Unito
EUR 58,96
Convertire valutaQuantità: 10 disponibili
Aggiungi al carrelloPaperback. Condizione: New.
Da: Revaluation Books, Exeter, Regno Unito
EUR 80,61
Convertire valutaQuantità: 2 disponibili
Aggiungi al carrelloPaperback. Condizione: Brand New. 275 pages. 9.50x6.25x0.75 inches. In Stock.
Da: Solr Books, Lincolnwood, IL, U.S.A.
EUR 42,13
Convertire valutaQuantità: 1 disponibili
Aggiungi al carrelloCondizione: very_good. This books is in Very good condition. There may be a few flaws like shelf wear and some light wear.
Da: moluna, Greven, Germania
EUR 48,37
Convertire valutaQuantità: Più di 20 disponibili
Aggiungi al carrelloCondizione: New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. Provides unique, comprehensive coverage of generalisation and regularisation: Provides the first real-world test results for recent theoretical findings on the generalisation performance of committeesConventional applications of neural networks usually .
Editore: Springer London, Springer London Feb 1999, 1999
ISBN 10: 1852330953 ISBN 13: 9781852330958
Lingua: Inglese
Da: buchversandmimpf2000, Emtmannsberg, BAYE, Germania
EUR 53,49
Convertire valutaQuantità: 1 disponibili
Aggiungi al carrelloTaschenbuch. Condizione: Neu. This item is printed on demand - Print on Demand Titel. Neuware -Conventional applications of neural networks usually predict a single value as a function of given inputs. In forecasting, for example, a standard objective is to predict the future value of some entity of interest on the basis of a time series of past measurements or observations. Typical training schemes aim to minimise the sum of squared deviations between predicted and actual values (the 'targets'), by which, ideally, the network learns the conditional mean of the target given the input. If the underlying conditional distribution is Gaus sian or at least unimodal, this may be a satisfactory approach. However, for a multimodal distribution, the conditional mean does not capture the relevant features of the system, and the prediction performance will, in general, be very poor. This calls for a more powerful and sophisticated model, which can learn the whole conditional probability distribution. Chapter 1 demonstrates that even for a deterministic system and 'be nign' Gaussian observational noise, the conditional distribution of a future observation, conditional on a set of past observations, can become strongly skewed and multimodal. In Chapter 2, a general neural network structure for modelling conditional probability densities is derived, and it is shown that a universal approximator for this extended task requires at least two hidden layers. A training scheme is developed from a maximum likelihood approach in Chapter 3, and the performance ofthis method is demonstrated on three stochastic time series in chapters 4 and 5.Springer Verlag GmbH, Tiergartenstr. 17, 69121 Heidelberg 300 pp. Englisch.
Da: THE SAINT BOOKSTORE, Southport, Regno Unito
EUR 68,53
Convertire valutaQuantità: Più di 20 disponibili
Aggiungi al carrelloPaperback / softback. Condizione: New. This item is printed on demand. New copy - Usually dispatched within 5-9 working days 497.
Da: BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Germania
EUR 85,55
Convertire valutaQuantità: 2 disponibili
Aggiungi al carrelloTaschenbuch. Condizione: Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -Conventional applications of neural networks usually predict a single value as a function of given inputs. In forecasting, for example, a standard objective is to predict the future value of some entity of interest on the basis of a time series of past measurements or observations. Typical training schemes aim to minimise the sum of squared deviations between predicted and actual values (the 'targets'), by which, ideally, the network learns the conditional mean of the target given the input. If the underlying conditional distribution is Gaus sian or at least unimodal, this may be a satisfactory approach. However, for a multimodal distribution, the conditional mean does not capture the relevant features of the system, and the prediction performance will, in general, be very poor. This calls for a more powerful and sophisticated model, which can learn the whole conditional probability distribution. Chapter 1 demonstrates that even for a deterministic system and 'be nign' Gaussian observational noise, the conditional distribution of a future observation, conditional on a set of past observations, can become strongly skewed and multimodal. In Chapter 2, a general neural network structure for modelling conditional probability densities is derived, and it is shown that a universal approximator for this extended task requires at least two hidden layers. A training scheme is developed from a maximum likelihood approach in Chapter 3, and the performance ofthis method is demonstrated on three stochastic time series in chapters 4 and 5. 300 pp. Englisch.