Sensitivity Analysis for Neural Networks [electronic resource] /by Daniel S. Yeung, Ian Cloete, Daming Shi, Wing W. Y. Ng.
by Yeung, Daniel S [author.]; Cloete, Ian [author.]; Shi, Daming [author.]; Ng, Wing W. Y [author.]; SpringerLink (Online service).
Material type:
BookSeries: Natural Computing Series: Publisher: Berlin, Heidelberg : Springer Berlin Heidelberg, 2010.Description: VIII, 86p. 24 illus. online resource.ISBN: 9783642025327.Subject(s): Computer science | Artificial intelligence | Computer simulation | Optical pattern recognition | Engineering design | Computer Science | Artificial Intelligence (incl. Robotics) | Control, Robotics, Mechatronics | Statistical Physics, Dynamical Systems and Complexity | Pattern Recognition | Simulation and Modeling | Engineering DesignDDC classification: 006.3 Online resources: Click here to access online | Item type | Current location | Call number | Status | Date due | Barcode |
|---|---|---|---|---|---|
| TJ210.2-211.495 (Browse shelf) | Available | ||||
| Long Loan | MAIN LIBRARY | Q334-342 (Browse shelf) | Available |
Close shelf browser
| R895-920 Ultrasonography in Vascular Diagnosis | QA75.5-76.95 Computer Music Modeling and Retrieval. Genesis of Meaning in Sound and Music | Q334-342 Sensitivity Analysis for Neural Networks | TJ210.2-211.495 Sensitivity Analysis for Neural Networks | Q334-342 Neural Networks and Micromechanics | TJ210.2-211.495 Neural Networks and Micromechanics | QA276-280 Experimental Methods for the Analysis of Optimization Algorithms |
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.
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.
There are no comments for this item.