Overview
- This is the first book to present a systematic description of sensitivity analysis methods for artificial neural networks.
- Includes supplementary material: sn.pub/extras
Part of the book series: Natural Computing Series (NCS)
Access this book
Tax calculation will be finalised at checkout
Other ways to access
Table of contents (8 chapters)
Keywords
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)Authors and Affiliations
Bibliographic Information
Book Title: Sensitivity Analysis for Neural Networks
Authors: Daniel S. Yeung, Ian Cloete, Daming Shi, Wing W. Y. Ng
Series Title: Natural Computing Series
DOI: https://doi.org/10.1007/978-3-642-02532-7
Publisher: Springer Berlin, Heidelberg
eBook Packages: Computer Science, Computer Science (R0)
Copyright Information: Springer-Verlag Berlin Heidelberg 2010
Hardcover ISBN: 978-3-642-02531-0Published: 18 November 2009
Softcover ISBN: 978-3-642-26139-8Published: 14 March 2012
eBook ISBN: 978-3-642-02532-7Published: 09 November 2009
Series ISSN: 1619-7127
Series E-ISSN: 2627-6461
Edition Number: 1
Number of Pages: VIII, 86
Number of Illustrations: 24 b/w illustrations
Topics: Artificial Intelligence, Control, Robotics, Mechatronics, Complex Systems, Pattern Recognition, Simulation and Modeling, Engineering Design