Le informazioni nella sezione "Riassunto" possono far riferimento a edizioni diverse di questo titolo.
Le informazioni nella sezione "Su questo libro" possono far riferimento a edizioni diverse di questo titolo.
Spese di spedizione:
GRATIS
In U.S.A.
Descrizione libro Soft Cover. Condizione: new. Codice articolo 9781852330958
Descrizione libro Condizione: New. PRINT ON DEMAND Book; New; Fast Shipping from the UK. No. book. Codice articolo ria9781852330958_lsuk
Descrizione libro Paperback. Condizione: Brand New. 275 pages. 9.50x6.25x0.75 inches. In Stock. Codice articolo x-1852330953
Descrizione libro Taschenbuch. 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. Codice articolo 9781852330958
Descrizione libro Kartoniert / Broschiert. Condizione: 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 . Codice articolo 4289360
Descrizione libro Taschenbuch. 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. Codice articolo 9781852330958
Descrizione libro PF. Condizione: New. Codice articolo 6666-IUK-9781852330958
Descrizione libro Paperback / softback. Condizione: New. This item is printed on demand. New copy - Usually dispatched within 5-9 working days. Codice articolo C9781852330958