.png){kind=logo}
Stock image for illustration purposes only - book cover, edition or condition may vary.
An Information-theoretic Approach To Neu
Deco, Gustavo; Obradovic, Dragan
€ 127.64
FREE Delivery in Ireland
Description for An Information-theoretic Approach To Neu
Paperback. Series: Perspectives in Neural Computing. Num Pages: 262 pages, biography. BIC Classification: UYQ. Category: (P) Professional & Vocational. Dimension: 234 x 156 x 15. Weight in Grams: 428.
Neural networks provide a powerful new technology to model and control nonlinear and complex systems. In this book, the authors present a detailed formulation of neural networks from the information-theoretic viewpoint. They show how this perspective provides new insights into the design theory of neural networks. In particular they show how these methods may be applied to the topics of supervised and unsupervised learning including feature extraction, linear and non-linear independent component analysis, and Boltzmann machines. Readers are assumed to have a basic understanding of neural networks, but all the relevant concepts from information theory are carefully introduced and explained. ... Read more
Neural networks provide a powerful new technology to model and control nonlinear and complex systems. In this book, the authors present a detailed formulation of neural networks from the information-theoretic viewpoint. They show how this perspective provides new insights into the design theory of neural networks. In particular they show how these methods may be applied to the topics of supervised and unsupervised learning including feature extraction, linear and non-linear independent component analysis, and Boltzmann machines. Readers are assumed to have a basic understanding of neural networks, but all the relevant concepts from information theory are carefully introduced and explained. ... Read more
Product Details
Format
Paperback
Publication date
2011
Publisher
Springer-Verlag New York Inc. United States
Number of pages
262
Condition
New
Series
Perspectives in Neural Computing
Number of Pages
262
Place of Publication
New York, NY, United States
ISBN
9781461284697
SKU
V9781461284697
Shipping Time
Usually ships in 15 to 20 working days
Ref
99-15
Reviews for An Information-theoretic Approach To Neu