Apress

Sensitivity Analysis for Neural Networks

By Daniel S. Yeung , Ian Cloete , Daming Shi , Wing W. Y. Ng

Sensitivity Analysis for Neural Networks Cover Image

This is the first book to present a systematic description of sensitivity analysis methods for artificial neural networks. It covers sensitivity analysis of multilayer perception neural networks and radial basis function neural networks.

Full Description

  • ISBN13: 978-3-6420-2531-0
  • 96 Pages
  • User Level: Science
  • Publication Date: November 9, 2009
  • Available eBook Formats: PDF
  • eBook Price: $129.00
Buy eBook Buy Print Book Add to Wishlist
Full Description
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.
Table of Contents

Table of Contents

  1. Introduction to Neural Networks.
  2. Principles of Sensitivity Analysis.
  3. Hyperrectangle Model.
  4. Sensitivity Analysis with Parameterized Activation Function.
  5. Localized Generalized Error Model.
  6. Critical Vector Learning Based on Sensitivity Analysis.
  7. Sensitivity Analysis of Prior Knowledge.
  8. Applications.
  9. References.
Errata

If you think that you've found an error in this book, please let us know about it. You will find any confirmed erratum below, so you can check if your concern has already been addressed.

* Required Fields

No errata are currently published