Haykin, Simon  <br/><br/>
Neural networks and learning machines 
Simon Haykin 
 - 3/e 
 - Noida  Pearson  2016 
 - 909p.  ill.,  24cm 
<br/><br/> Rosenblatt's perceptron --<br/>  Model building through regression --<br/>  The least-mean-square algorithm --<br/>  Multilayer perceptrons --<br/>  Kernel methods and radial-basis function networks --<br/>  Support vector machines --<br/>  Regularization theory --<br/>  Principal-components analysis --<br/><br/>  Self-organizing maps --<br/>  Information-theoretic learning models --  Stochastic methods rooted in statistical mechanics --<br/><br/>  Dynamic programming --  Neurodynamics --<br/>  Bayseian filtering for state estimation of dynamic systems --<br/>  Dynamically driven recurrent networks. 
<br/><br/> Using a wealth of case studies to illustrate the real-life, practical applications of neural networks, this state-of-the-art text exposes students to many facets of Neural Networks 
<br/><br/><label>ISBN: </label>9789332570313 
<br/><br/><label>Subjects--Topical Terms: </label><br/>Neural networks (Computer science) <br/>Neural networks (Computer science) -- Problems, exercises, etc.<br/> Lernendes System
<br/><br/><label>Dewey Class. No.: </label>004.89   / HAY