Information theoretic learning : Renyi's entropy and kernel perspectives / José C. Principe.
Information Theoretic Learning (ITL) is a framework where the conventional concepts of second order statistics (covariance, L2 distances, correlation functions) are substituted by scalars and functions with information theoretic underpinnings. This book deals with the ITL algorithms to adapt linear...
Saved in:
| Main Author: | |
|---|---|
| Format: | Ebook |
| Language: | English |
| Published: |
New York ; London :
Springer,
[2010]
|
| Series: | Information science and statistics.
|
| Subjects: | |
| Online Access: | Springer eBooks |
| Summary: | Information Theoretic Learning (ITL) is a framework where the conventional concepts of second order statistics (covariance, L2 distances, correlation functions) are substituted by scalars and functions with information theoretic underpinnings. This book deals with the ITL algorithms to adapt linear or nonlinear learning machines. |
|---|---|
| Physical Description: | 1 online resource (xxii, 515 pages) : illustrations. |
| Bibliography: | Includes bibliographical references. |
| ISSN: | 1613-9011 |