000			03446nam a22005655i 4500
001			u373450
003			SIRSI
005			20160812084146.0
007			cr nn 008mamaa
008			100301s2010 gw | s |||| 0|eng d
020			_a9783642025327 _9978-3-642-02532-7
040			_cMX-MeUAM
050		4	_aQ334-342
050		4	_aTJ210.2-211.495
082	0	4	_a006.3 _223
100	1		_aYeung, Daniel S. _eauthor.
245	1	0	_aSensitivity Analysis for Neural Networks _h[recurso electrónico] / _cby Daniel S. Yeung, Ian Cloete, Daming Shi, Wing W. Y. Ng.
264		1	_aBerlin, Heidelberg : _bSpringer Berlin Heidelberg, _c2010.
300			_aVIII, 86p. 24 illus. _bonline resource.
336			_atext _btxt _2rdacontent
337			_acomputer _bc _2rdamedia
338			_aonline resource _bcr _2rdacarrier
347			_atext file _bPDF _2rda
490	1		_aNatural Computing Series, _x1619-7127
505	0		_ato 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.
520			_aArtificial 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.
650		0	_aComputer science.
650		0	_aArtificial intelligence.
650		0	_aComputer simulation.
650		0	_aOptical pattern recognition.
650		0	_aEngineering design.
650	1	4	_aComputer Science.
650	2	4	_aArtificial Intelligence (incl. Robotics).
650	2	4	_aControl, Robotics, Mechatronics.
650	2	4	_aStatistical Physics, Dynamical Systems and Complexity.
650	2	4	_aPattern Recognition.
650	2	4	_aSimulation and Modeling.
650	2	4	_aEngineering Design.
700	1		_aCloete, Ian. _eauthor.
700	1		_aShi, Daming. _eauthor.
700	1		_aNg, Wing W. Y. _eauthor.
710	2		_aSpringerLink (Online service)
773	0		_tSpringer eBooks
776	0	8	_iPrinted edition: _z9783642025310
830		0	_aNatural Computing Series, _x1619-7127
856	4	0	_zLibro electrónico _uhttp://148.231.10.114:2048/login?url=http://link.springer.com/book/10.1007/978-3-642-02532-7
596			_a19
942			_cLIBRO_ELEC
999			_c201330 _d201330