000			02576cam a22002774a 4500
008			100314s2009 enka b 001 0 eng
020			_a9780131293762
020			_a0131293761
035			_a(Sirsi) u4904
040			_aEG-CaNU _c EG-CaNU _d EG-CaNU
042			_ancode
082	0	4	_a006.32 _2 22
100	1		_aHaykin, Simon S., _d 1931- _9318
245	1	0	_aNeural networks and learning machines / _c Simon Haykin.
250			_a3rd ed. / _b International ed.
260			_aHarlow ; _a London : _b Pearson Education, _c 2009.
300			_a934 p. : _b ill. ; _c 23 cm.
500			_aPrevious ed.: published as Neural networks. Upper Saddle River, N.J.: Prentice Hall, 1999.
504			_aIncludes bibliographical references and index.
505	0		_aPreface x -- Introduction 1 -- Chapter 1 Rosenblatt’s Perceptron 47 -- Chapter 2 Model Building through Regression 68 -- Chapter 3 The Least-Mean-Square Algorithm 91 -- Chapter 4 Multilayer Perceptrons 122 -- Chapter 5 Kernel Methods and Radial-Basis Function Networks 230 -- Chapter 6 Support Vector Machines 268 -- Chapter 7 Regularization Theory 313 -- Chapter 8 Principal-Components Analysis 367 -- Chapter 9 Self-Organizing Maps 425 -- Chapter 10 Information-Theoretic Learning Models 475 -- Chapter 11 Stochastic Methods Rooted in Statistical Mechanics 579 -- Chapter 12 Dynamic Programming 627 -- Chapter 13 Neurodynamics 672 -- Chapter 14 Bayseian Filtering for State Estimation of Dynamic Systems 731 -- Chapter 15 Dynamically Driven Recurrent Networks 790
520			_aFor graduate-level neural network courses offered in the departments of Computer Engineering, Electrical Engineering, and Computer Science. Renowned for its thoroughness and readability, this well-organized and completely up-to-date text remains the most comprehensive treatment of neural networks from an engineering perspective. Matlab codes used for the computer experiments in the text are available for download at: http://www.pearsonhighered.com/haykin/ Refocused, revised and renamed to reflect the duality of neural networks and learning machines, this edition recognizes that the subject matter is richer when these topics are studied together. Ideas drawn from neural networks and machine learning are hybridized to perform improved learning tasks beyond the capability of either independently.
650		0	_aNeural networks (Computer science) _91507
650		0	_aNeural networks (Computer science) _v Problems, exercises, etc. _91507
700	1		_aHaykin, Simon S., _d 1931- _t Neural networks. _9318
596			_a1
999			_c3905 _d3905