Synopses & Reviews
A comprehensive look at learning and generalization theory. The statistical theory of learning and generalization concerns the problem of choosing desired functions on the basis of empirical data. Highly applicable to a variety of computer science and robotics fields, this book offers lucid coverage of the theory as a whole. Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
Includes bibliographical references (p. 723-732) and index.
Table of Contents
Partial table of contents:
THEORY OF LEARNING AND GENERALIZATION.
Two Approaches to the Learning Problem.
Estimation of the Probability Measure and Problem of Learning.
Conditions for Consistency of Empirical Risk Minimization Principle.
The Structural Risk Minimization Principle.
Stochastic Ill-Posed Problems.
SUPPORT VECTOR ESTIMATION OF FUNCTIONS.
Perceptrons and Their Generalizations.
SV Machines for Function Approximations, Regression Estimation, and Signal Processing.
STATISTICAL FOUNDATION OF LEARNING THEORY.
Necessary and Sufficient Conditions for Uniform Convergence of Frequencies to Their Probabilities.
Necessary and Sufficient Conditions for Uniform One-Sided Convergence of Means to Their Expectations.
Comments and Bibliographical Remarks.