Learning Theory

An Approximation Theory Viewpoint

AvFelipe Cucker,Ding Xuan Zhou

Inbunden, Engelska, 2007

Del 24 i serien Cambridge Monographs on Applied and Computational Mathematics

1 065 kr

Beställningsvara. Skickas inom 7-10 vardagar. Fri frakt över 249 kr.

Beskrivning

The goal of learning theory is to approximate a function from sample values. To attain this goal learning theory draws on a variety of diverse subjects, specifically statistics, approximation theory, and algorithmics. Ideas from all these areas blended to form a subject whose many successful applications have triggered a rapid growth during the last two decades. This is the first book to give a general overview of the theoretical foundations of the subject emphasizing the approximation theory, while still giving a balanced overview. It is based on courses taught by the authors, and is reasonably self-contained so will appeal to a broad spectrum of researchers in learning theory and adjacent fields. It will also serve as an introduction for graduate students and others entering the field, who wish to see how the problems raised in learning theory relate to other disciplines.

Produktinformation

Utgivningsdatum:2007-03-29
Mått:160 x 231 x 17 mm
Vikt:360 g
Format:Inbunden
Språk:Engelska
Serie:Cambridge Monographs on Applied and Computational Mathematics
Antal sidor:238
Förlag:Cambridge University Press
ISBN:9780521865593

Utforska kategorier

Systemvetenskap och AI inom Data och IT

Mer om författaren

Felipe Cucker is a Professor of Mathematics at the City University of Hong Kong. Ding Xuan Zhou is an Associate Professor in the Department of Mathematics at the City University of Hong Kong.

Recensioner i media

'The book is well suited for its target audience, which includes researchers and graduate students. They will, no doubt, be reassured to find that each chapter closes with a collection of references and additional remarks, which place the preceding information in a wider context. … Overall, this text is another excellent addition to the Applied and Computational Mathematics series published by Cambridge University Press. It complements other titles in the series without duplicating material and should be of value to anyone interested in learning theory or a neighbouring field.' Mathematics Today

Innehållsförteckning

Preface; Foreword; 1. The framework of learning; 2. Basic hypothesis spaces; 3. Estimating the sample error; 4. Polynomial decay approximation error; 5. Estimating covering numbers; 6. Logarithmic decay approximation error; 7. On the bias-variance problem; 8. Regularization; 9. Support vector machines for classification; 10. General regularized classifiers; Bibliography; Index.