Verlag: Cambridge University Press (edition ), 2006
ISBN 10: 0521841089 ISBN 13: 9780521841085
Sprache: Englisch
Anbieter: BooksRun, Philadelphia, PA, USA
Hardcover. Zustand: Fair. The item might be beaten up but readable. May contain markings or highlighting, as well as stains, bent corners, or any other major defect, but the text is not obscured in any way.
Verlag: Cambridge University Press, 2006
ISBN 10: 0521841089 ISBN 13: 9780521841085
Sprache: Englisch
Anbieter: Books From California, Simi Valley, CA, USA
hardcover. Zustand: Very Good.
Verlag: Cambridge University Press, 2006
ISBN 10: 0521841089 ISBN 13: 9780521841085
Sprache: Englisch
Anbieter: Majestic Books, Hounslow, Vereinigtes Königreich
EUR 108,92
Anzahl: 1 verfügbar
In den WarenkorbZustand: New. pp. xii + 394 Illus.
EUR 129,92
Anzahl: 2 verfügbar
In den WarenkorbHardcover. Zustand: Brand New. new title edition. 406 pages. 10.00x7.00x1.00 inches. In Stock.
Verlag: Cambridge University Press, 2006
ISBN 10: 0521841089 ISBN 13: 9780521841085
Sprache: Englisch
Anbieter: AHA-BUCH GmbH, Einbeck, Deutschland
Buch. Zustand: Neu. Druck auf Anfrage Neuware - Printed after ordering - This important new text and reference for researchers and students in machine learning, game theory, statistics and information theory offers the first comprehensive treatment of the problem of predicting individual sequences. Unlike standard statistical approaches to forecasting, prediction of individual sequences does not impose any probabilistic assumption on the data-generating mechanism. Yet, prediction algorithms can be constructed that work well for all possible sequences, in the sense that their performance is always nearly as good as the best forecasting strategy in a given reference class. The central theme is the model of prediction using expert advice, a general framework within which many related problems can be cast and discussed. Repeated game playing, adaptive data compression, sequential investment in the stock market, sequential pattern analysis, and several other problems are viewed as instances of the experts' framework and analyzed from a common nonstochastic standpoint that often reveals new and intriguing connections. Old and new forecasting methods are described in a mathematically precise way in order to characterize their theoretical limitations and possibilities.