Sensitivity Analysis for Neural Networks - Rilegato

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

Rilegato

ISBN 10: 3642025315 ISBN 13: 9783642025310

Casa editrice: Springer-Verlag New York Inc, 2009

Riassunto

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.

Su questo libro

Recensione

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)

Contenuti

to Neural Networks.- Principles of Sensitivity Analysis.- Hyper-Rectangle Model.- Sensitivity Analysis with Parameterized Activation Function.- Localized Generalization Error Model.- Critical Vector Learning for RBF Networks.- Sensitivity Analysis of Prior Knowledge1.- Applications.

Dettagli dell?edizione

• Editore: Springer-Verlag New York Inc
• Data di pubblicazione: 2009
• Lingua: Inglese
• ISBN 10: 3642025315
• ISBN 13: 9783642025310
• Rilegatura: Copertina rigida
• Numero edizione: 1
• Numero di pagine: 86
• Contatto del produttore: {language_tag:it_IT,value:"Springer Nature Customer Service Center GmbH; ProductSafety@springernature.com"}