HAPPY HOLIDAYS: Get a special discount on Apress Access! Subscribe today >>

Natural Computing Series

Sensitivity Analysis for Neural Networks

Authors: Yeung, D.S., Cloete, I., Shi, D., Ng, W.W.Y.

  • This is the first book to present a systematic description of sensitivity analysis methods for artificial neural networks.

Buy this book

eBook $129.00
price for USA
  • ISBN 978-3-642-02532-7
  • Digitally watermarked, DRM-free
  • Included format: PDF, EPUB
  • ebooks can be used on all reading devices
  • Download immediately after purchase
Hardcover $169.00
price for USA
  • ISBN 978-3-642-02531-0
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Softcover $169.00
price for USA
  • ISBN 978-3-642-26139-8
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
About this book

Artificial neural networks are used to model systems that receive inputs and produce outputs. The relationships between the inputs and outputs and the representation parameters are critical issues in the design of related engineering systems, and sensitivity analysis concerns methods for analyzing these relationships. Perturbations of neural networks are caused by machine imprecision, and they can be simulated by embedding disturbances in the original inputs or connection weights, allowing us to study the characteristics of a function under small perturbations of its parameters.

This is the first book to present a systematic description of sensitivity analysis methods for artificial neural networks. It covers sensitivity analysis of multilayer perceptron neural networks and radial basis function neural networks, two widely used models in the machine learning field. The authors examine the applications of such analysis in tasks such as feature selection, sample reduction, and network optimization. The book will be useful for engineers applying neural network sensitivity analysis to solve practical problems, and for researchers interested in foundational problems in neural networks.

Reviews

From the reviews:

“Neural Networks are seen as an information paradigm inspired by the way the human brain processes information. … The book may be used by researchers in diverse domains, such as neural networks, machine learning, computer engineering, etc., facing problems connected to sensitivity analysis of neural networks.” (Florin Gorunescu, Zentralblatt MATH, Vol. 1189, 2010)

Table of contents (8 chapters)

  • Introduction to Neural Networks

    Yeung, Daniel S. (et al.)

    Pages 1-15

  • Principles of Sensitivity Analysis

    Yeung, Daniel S. (et al.)

    Pages 17-24

  • Hyper-Rectangle Model

    Yeung, Daniel S. (et al.)

    Pages 25-27

  • Sensitivity Analysis with Parameterized Activation Function

    Yeung, Daniel S. (et al.)

    Pages 29-31

  • Localized Generalization Error Model

    Yeung, Daniel S. (et al.)

    Pages 33-46

Buy this book

eBook $129.00
price for USA
  • ISBN 978-3-642-02532-7
  • Digitally watermarked, DRM-free
  • Included format: PDF, EPUB
  • ebooks can be used on all reading devices
  • Download immediately after purchase
Hardcover $169.00
price for USA
  • ISBN 978-3-642-02531-0
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Softcover $169.00
price for USA
  • ISBN 978-3-642-26139-8
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Loading...

Bibliographic Information

Bibliographic Information
Book Title
Sensitivity Analysis for Neural Networks
Authors
Series Title
Natural Computing Series
Copyright
2010
Publisher
Springer-Verlag Berlin Heidelberg
Copyright Holder
Springer-Verlag Berlin Heidelberg
eBook ISBN
978-3-642-02532-7
DOI
10.1007/978-3-642-02532-7
Hardcover ISBN
978-3-642-02531-0
Softcover ISBN
978-3-642-26139-8
Series ISSN
1619-7127
Edition Number
1
Number of Pages
VIII, 86
Number of Illustrations and Tables
24 b/w illustrations
Topics