Pattern Recognition Using Neural Networks: Theory and Algorithms for Engineers a

Description: Pattern Recognition Using Neural Networks by Looney A text covering traditional linear pattern recognition and its nonlinear extension via neural networks. The approach is algorithmic for easy implementation on a computer. It covers the standard decision-theoretic pattern recognition of clustering via minimum distance, graphical and structural methods, and Bayesian discrimination. FORMAT Hardcover LANGUAGE English CONDITION Brand New Publisher Description Pattern Recognition Using Neural Networks covers traditional linear pattern recognition and its nonlinear extension via neural networks. The approach is algorithmic for easy implementation on a computer, which makes this a refreshing what-why-and-how text that contrasts with the theoretical approach and pie-in-the-sky hyperbole of many books on neural networks. It covers the standard decision-theoretic pattern recognition of clustering via minimum distance,graphical and structural methods, and Bayesian discrimination. Pattern recognizers evolve across the sections into perceptrons, a layer of perceptrons, multiple-layered perceptrons, functionallink nets, and radial basis function networks. Other networks covered in the process are learning vector quantization networks, self-organizing maps, and recursive neural networks. Backpropagation is derived in complete detail for one and two hidden layers for both unipolar and bipolar sigmoid activation functions. The more efficient fullpropagation, quickpropagation, cascade correlation, and various methods such as strategic search, conjugate gradients, and genetic algorithms are described.Advanced methods are also described, including the full training algorithms for radial basis function networks and random vector functional link nets, as well as competitive learning networks and fuzzyclustering algorithms. Special topics covered include: feature engineering data engineering neural engineering of network architectures validation and verification of the trained networks This textbook is ideally suited for a senior undergraduate or graduate course in pattern recognition or neural networks for students in computer science, electrical engineering, and computer engineering. It is also a useful reference andresource for researchers and professionals. Author Biography Carl G. Looney is at University of Nevada. Table of Contents PrefaceList of TablesPart I. FUNDAMENTALS OF PATTERN RECOGNITION0.: Basic Concepts of Pattern Recognition1.: Decision-Theoretic Algorithms2.: Structural Pattern RecognitionPart II. INTRODUCTORY NEURAL NETWORKS3.: Artificial Neural Network Structures4.: Supervised Training via Error Backpropagation: DerivationsPART III. ADVANCED FUNDAMENTALS OF NEURAL NETWORKS5.: Acceleration and Stabilization of Supervised Gradient Training of MLPs6.: Supervised Training via Strategic Search7.: Advances in Network Algorithms for Classification and Recognition8.: Recurrent Neural NetworksPART IV. NEURAL, FEATURE, AND DATA ENGINEERING9.: Neural Engineering and Testing of FANNs10.: Feature and Data EngineeringPART IV. TESTING AND APPLICATIONS11.: Some Comparative Studies of Feedforward Artificial Neural Networks12.: Pattern Recognition Applications Review "Pattern Recognition Using Neural Networks makes its subject easy to understand by offering intuitive explanations and examples. ...an excellent resource for those who want to implement neural networks, rather than just learn the theory."--Mark Kvale,"Really good text for students and professionals."--Aiy Farag, University of Louisville Long Description Pattern Recognition Using Neural Networks covers traditional linear pattern recognition and its nonlinear extension via neural networks. The approach is algorithmic for easy implementation on a computer, which makes this a refreshing what-why-and-how text that contrasts with the theoretical approach and pie-in-the-sky hyperbole of many books on neural networks. It covers the standard decision-theoretic pattern recognition of clustering via minimum distance,graphical and structural methods, and Bayesian discrimination. Pattern recognizers evolve across the sections into perceptrons, a layer of perceptrons, multiple-layered perceptrons, functional link nets, and radial basis function networks. Other networks covered in the process are learningvector quantization networks, self-organizing maps, and recursive neural networks. Backpropagation is derived in complete detail for one and two hidden layers for both unipolar and bipolar sigmoid activation functions. The more efficient fullpropagation, quickpropagation, cascade correlation, and various methods such as strategic search, conjugate gradients, and genetic algorithms are described. Advanced methods are also described, including the full training algorithms for radial basisfunction networks and random vector functional link nets, as well as competitive learning networks and fuzzy clustering algorithms. Special topics covered include: feature engineering data engineering neural engineering of network architecturesvalidation and verification of the trained networks This textbook is ideally suited for a senior undergraduate or graduate course in pattern recognition or neural networks for students in computer science, electrical engineering, and computer engineering. It is also a useful reference and resource for researchers and professionals. Review Text "Pattern Recognition Using Neural Networks makes its subject easy to understand by offering intuitive explanations and examples. ...an excellent resource for those who want to implement neural networks, rather than just learn the theory."--Mark Kvale,"Really good text for students and professionals."--Aiy Farag, University of Louisville Review Quote "Really good text for students and professionals."--Aiy Farag, Universityof Louisville Feature Offers a unique, hands-on, real-world approach using algorithms that can easily be implemented on a computer Covers widely differing recognition applications, from image processing and speech recognition to texture recognition and football betting, which suggest new applications and techniques to students Analyzes the internals of the network "black boxes" so that students can understand and use them judiciously to perform recognition Details ISBN0195079205 Short Title PATTERN RECOGNITION USING NEUR Language English ISBN-10 0195079205 ISBN-13 9780195079203 Media Book Format Hardcover DEWEY 006.4 Year 1997 Subtitle Theory and Algorithms for Engineers and Scientists Country of Publication United States Imprint Oxford University Press Inc Place of Publication New York Pages 480 DOI 10.1604/9780195079203 AU Release Date 1997-02-20 NZ Release Date 1997-02-20 US Release Date 1997-02-20 UK Release Date 1997-02-20 Author Looney Publisher Oxford University Press Inc Publication Date 1997-02-20 Illustrations numerous line figures, tables Audience Tertiary & Higher Education We've got this At The Nile, if you're looking for it, we've got it. With fast shipping, low prices, friendly service and well over a million items - you're bound to find what you want, at a price you'll love! TheNile_Item_ID:127216501;

Price: 438.61 AUD

Location: Melbourne

End Time: 2024-11-15T03:02:00.000Z

Shipping Cost: 17.48 AUD