Advances in learning theory : methods, models and applications /

Show other versions (1)

This text details advances in learning theory that relate to problems studied in neural networks, machine learning, mathematics and statistics.

Bibliographic Details
Call Number:Libro Electrónico
Corporate Author: NATO Advanced Study Institute on Learning Theory and Practice Louvain, Belgium
Other Authors: Suykens, Johan A. K.
Format: Electronic Conference Proceeding eBook
Language:Inglés
Published: Amsterdam ; Washington, DC : Tokyo : IOS Press ; Ohmsha, ©2003.
Series:NATO science series. Computer and systems sciences ; v. 190.
Subjects:
Computational learning theory > Congresses.
Machine learning > Mathematical models > Congresses.
Théorie de l'apprentissage informatique > Congrès.
Apprentissage automatique > Modèles mathématiques > Congrès.
COMPUTERS > Enterprise Applications > Business Intelligence Tools.
COMPUTERS > Intelligence (AI) & Semantics.
Computational learning theory
Machine learning > Mathematical models
Conference papers and proceedings
Online Access:Texto completo
Table of Contents:
  • Cover; Title page; Preface; Organizing committee; List of chapter contributors; Contents; 1 An Overview of Statistical Learning Theory; 2 Best Choices for Regularization Parameters in Learning Theory: On the Bias-Variance Problem; 3 Cucker Smale Learning Theory in Besov Spaces; 4 High-dimensional Approximation by Neural Networks; 5 Functional Learning through Kernels; 6 Leave-one-out Error and Stability of Learning Algorithms with Applications; 7 Regularized Least-Squares Classification; 8 Support Vector Machines: Least Squares Approaches and Extensions.

Similar Items