Subspace Learning of Neural Networks - Cheng Lv, Jian; Yi, Zhang; Zhou, Jiliu; - Prospero Internet Bookshop

Subspace Learning of Neural Networks
 
Product details:

ISBN13:9781439815359
ISBN10:1439815356
Binding:Hardback
No. of pages:256 pages
Size:234x156 mm
Weight:500 g
Language:English
Illustrations: 84 Illustrations, black & white; 5 Tables, black & white
0
Category:

Subspace Learning of Neural Networks

 
Edition number: 1
Publisher: CRC Press
Date of Publication:
 
Normal price:

Publisher's listprice:
GBP 130.00
Estimated price in HUF:
68 250 HUF (65 000 HUF + 5% VAT)
Why estimated?
 
Your price:

61 425 (58 500 HUF + 5% VAT )
discount is: 10% (approx 6 825 HUF off)
The discount is only available for 'Alert of Favourite Topics' newsletter recipients.
Click here to subscribe.
 
Availability:

Estimated delivery time: In stock at the publisher, but not at Prospero's office. Delivery time approx. 3-5 weeks.
Not in stock at Prospero.
Can't you provide more accurate information?
 
  Piece(s)

 
Short description:

Using real-life examples to illustrate the performance of learning algorithms and instructing readers how to apply them to practical applications, this work offers a comprehensive treatment of subspace learning algorithms for neural networks. The authors summarize a decade of high quality research offering a host of practical applications. They demonstrate ways to extend the use of algorithms to fields such as encryption communication, data mining, computer vision, and signal and image processing to name just a few. The brilliance of the work lies with how it coherently builds a theoretical understanding of the convergence behavior of subspace learning algorithms through a summary of chaotic behaviors.

Long description:

Using real-life examples to illustrate the performance of learning algorithms and instructing readers how to apply them to practical applications, this work offers a comprehensive treatment of subspace learning algorithms for neural networks. The authors summarize a decade of high quality research offering a host of practical applications. They demonstrate ways to extend the use of algorithms to fields such as encryption communication, data mining, computer vision, and signal and image processing to name just a few. The brilliance of the work lies with how it coherently builds a theoretical understanding of the convergence behavior of subspace learning algorithms through a summary of chaotic behaviors.

Table of Contents:

Introduction. PCA Learning Algorithms with Constants Learning Rates. PCA Learning Algorithms with Adaptive Learning Rates. GHA PCA Learning Algorithms. MCA Learning Algorithms. ICA Learning Algorithms. Chaotic Behaviors Arising from Learning Algorithms. Multi-Block-Based MCA for Nonlinear Surface Fitting. A ICA Algorithm for Extracting Fetal Electrocardiogram. Some Applications of PCA Neural Networks. Conclusion.