Advanced Search

Query:

Fill in the form and click »Search«...

Format:

Display: entries per page entries

Zbl 0833.62008
Vapnik, Vladimir N.
The nature of statistical learning theory. (English)
[B] Berlin: Springer-Verlag. xv, 188 p. DM 58.00; öS 423.40; sFr 56.00 (1995). ISBN 0-387-94559-8

The goal of this book is to describe the nature of statistical learning theory which includes (i) Concepts describing the necessary and sufficient conditions for consistency of inference, (ii) Bounds describing the generalizing ability of learning machines, (iii) Inductive inference for small sample sizes, (iv) Methods for implementing this new type of inference. The author's main target is to show how the abstract reasoning implies new algorithms. He concentrates on understanding the nature of the problem and the new theory as a whole.\par The contents of the book show an introduction, five chapters, informal reasoning and comments, respectively. The introduction describes the history of research of the learning problem which can be separated into four periods. Ch. 1 is of fundamental importance for understanding the new philosophy and the concepts for constructing necessary and sufficient conditions for consistency of the learning process. This is considered as a problem of finding a desired dependence using a limited number of observations. Regression estimation, risk minimization, pattern recognition, and density estimation yield different formulations of the learning problem.\par Ch. 2 concentrates on consistency as part of the learning theory. A conceptual model for learning processes that are based on the Empirical Risk Minimization (ERM) inductive principle is described. For better understanding the ERM principle theorems about the idea of nonfalsifiability are given. Concepts that allow the construction of the consistency conditions mentioned above are discussed.\par Ch. 3 describes the nonasymptotic theory of bounds on the convergence rate of the learning processes. The bounds are based on two different capacity concepts described in the conceptual model of Ch. 2: The Annealed Entropy function and the Growth function which result in distribution-dependent bounds and distribution-independent bounds, respectively.\par Ch. 4 is devoted to small sample sizes. To construct small sample sizes the bounds for the generalization ability of learning machines with sets of unbounded functions are used. MDL (Minimum Description Length) and SRM (Structural Risk Minimization) principles of inductive inference for small sample sizes are discussed under the aspect of algorithmic complexity.\par Ch. 5 describes learning algorithms for pattern recognition where the classical concepts of neural networks are considered. A new type of universal learning machine, the Support Vector Machine which realizes the SRM inductive principle is introduced. Finally, in the conclusion some open problems of learning theory are discussed.\par The book is written in a well readable and concise style with special emphasis on the practical power of abstract reasoning. It is to recommend to students, engineers and scientists of different backgrounds like statisticians, mathematicians, physicists, and computer scientists.
[R.Fahrion (Heidelberg)]

MSC 2000:: *62B10 Statistical information theory
62-02 Research monographs (statistics)
68T05 Learning and adaptive systems
62-01 Textbooks (statistics)

Keywords: regression estimation; empirical risk minimization; annealed entropy function; growth function; structural risk minimization; support vector machine; statistical learning theory; consistency of inference; generalizing ability of learning machines; algorithms; risk minimization; pattern recognition; density estimation; nonfalsifiability; convergence rate; capacity concepts; distribution-dependent bounds; distribution- independent bounds; small sample sizes; algorithmic complexity; neural networks; universal learning machine; abstract reasoning

Cited in: Zbl 1205.91139 Zbl 1202.91352 Zbl 1014.68133 Zbl 0970.62017 Zbl 0934.62009 Zbl pre06148107

Comment on this Item PDF MathML XML ASCII DVI PS BibTeX Online Ordering

	Scientific prize winners of the ICM 2010
	Overhang
	Lie groups, physics and geometry. An introduction for physicists, engineers and chemists.

Advanced Search

Zentralblatt MATH Berlin [Germany]