Books

Adaptive Resonance Theory Microchips describes circuit strategies resulting in efficient and functional adaptive resonance theory (ART) hardware systems. While ART algorithms have been developed in software by their creators, this is the first book that addresses efficient VLSI design of ART systems.

Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabé; Andreou, Andreas G. Kluwer Academic Publishers, Boston Hardbound, ISBN 0-7923-8231-5 August 1998, 264 pp.

The main aim of this book is to report a very small sample of the research on the evolution of ART neural network and its applications. Other aspects of research may be found in publications listed in the Downloads section of this site.

Series: Studies in Fuzziness and Soft Computing, Vol. 43 Jain, Lakhmi C.; Lazzerini, Beatrice; Halici, Ugur (Eds.) 2000, XII, 258 pp. 69 figs., 30 tabs., Hardcover ISBN: 3-7908-1270-6

In this very successfull textbook ART family of models is extensively covered in Chapter 6, entitled "Coding and Categorization". Variations described include Adaptive Resonance Theory principles as well as ART1, 2, 3 and ARTMAP neural networks.

Lawrence ErlbaumAssociates, Inc. SubTitle: Second Edition Author/Editor: Daniel S. Levine ISBN: 0-8058-2005-1 Year: 2000 Binding: Hardcover Page Count: 512

The book discribes the organization of memory in the brain. It is a coherent accound, useful for a modelers that wants to use ART as well as someone interested in the historical development of memory research.

Larry R. Squire, Professor of Psychiatry, University of California, San Diego ISBN: 0-19-504208-5 Publication date: 10 September 1987 Paperback 336 pages, 58 illustrations, 234mm x 156mm

This is an advanced collection of the recent models of music, their analysis and juxtaposition. ART-related material can be found in Part I subsection entitled "Modeling Pitch Perception with Adaptive Resonance Theory Artificial Neural Networks" and in Part III subsection entitled "Pitch-based Streaming in Auditory Perception."

Niall Griffith and Peter M. Todd (Eds.) March 1999 ISBN 0-262-07181-9 385 pp., 75 illus.

This is a brief introduction to basic concepts followed by an in-depth coverage of density estimation, error functions, parameter optimization algorithms, data pre-processing, and Bayesian methods among other pattern-recognition techniques.

Neural Networks for Pattern Recognition By Christopher M. Bishop Edition: reprint Published by Oxford University Press, 2005 ISBN 0198538642, 9780198538646 482 pages

Neurocomputing 2 collects forty-one articles covering network architecture, neurobiological computation, statistics and pattern classification, and problems and applications that suggest important directions for the evolution of neurocomputing.

James A. Anderson, Andras Pellionisz and Edward Rosenfeld (Eds.) August 1993 ISBN 0-262-51075-8 Hardcover, 750 pp.

Researchers will find Neurocomputing an essential guide to the concepts employed in this field that have been taken from disciplines as varied as neuroscience, psychology, cognitive science, engineering, and physics. A number of these important historical papers contain ideas that have not yet been fully exploited, while the more recent articles define the current direction of neurocomputing and point to future research. Each article has an introduction that places it in historical and intellectual perspective.

By James Arthur Anderson, Edward Rosenfeld Contributor James A. Anderson, Andras Pellionisz, Edward Rosenfeld Published by MIT Press, 1988 ISBN 0262010976, 9780262010979

Pattern recognition systems play a role in applications as diverse as speech recognition, optical character recognition, image processing, and signal analysis. This reference provides information needed to choose the most appropriate of the many available techniques for a given class of problems. The latest edition includes explanations of classical and new methods, including neural networks, stochastic methods, genetic algorithms, and theory of learning. It provides algorithms to explain specific pattern-recognition and learning techniques as well as appendices covering the necessary mathematical background. ART is described in detail in Chapter 10, entitled "Unsupervised Learning and Clustering", section 10.11.2.

By Richard O. Duda, Peter E. Hart, David G. Stork Contributor Richard O. Duda, Peter E. Hart, David G. Stork Edition: 2, illustrated Published by Wiley, 2001 Original from the University of Michigan Digitized Nov 16, 2007 ISBN 0471056693, 9780471056690 654 pages

This is the "Bible" of Neuroscience. This Fourth Edition (2000) covers everything from molecular biology to motion, to memory and cognition it is the utimate source of information for researchers, medical students as well as modelers and practitioners.

By Eric R. Kandel, James Harris Schwartz, Thomas M. Jessell Edition: 4, illustrated Published by McGraw-Hill Professional, 2000 ISBN 0838577016, 9780838577011 1414 pages

"Principles of Neurocomputing for Science and Engineering" is written specifically for scientists and engineers who want to apply neural networks to solve complex problems. For each neurocomputing concept, a solid mathematical foundation is presented along with illustrative examples to accompany that particular architecture and associated training algorithm. Chapter 4 is devoted to the self-organizing neural networks. ART model is presented in section 4.4. ART1 network is presented in detail.

Fredric M. Ham, Florida Institute of Technology--Melbourne Ivica Kostanic, Agilent Technologies, Inc. ISBN: 0-07-025966-6 Published by McGraw-Hill Education, 2001 Hardcover / 672 pages

This book is an account of the scientific research in psychology and neuroscience spanning the last two decades. Based on the case studies and everyday examples, it is a well-written overview intended for a memory modeler interested in understanding of where the models emanate from.

By Daniel L. Schacter Edition: reprint, illustrated Published by BasicBooks, 1996 ISBN 0465075525, 9780465075522 398 pages

Boston Studies in the Philosophy of Science Series, Volume 70 Neural Principles of Learning, Perceptin, Development, Cognition and Motor Control ART model plays a central role in this volume of works as it lays a foundation for the understanding of the various brain functionalities. ART is cited on pages: 1, 2, 29, 31, 230, 382, 425, 449, 498, 558, 561, 606, and 630.

Studies of Mind and Brain: Neural Principles of Learning, Perception, Development, Cognition, and Motor Control By Stephen Grossberg Edition: illustrated Published by Kluwer Boston, 1982 ISBN 9027713596, 9789027713599 662 pages

In this book the scientists that shaped the field of neural networks talk about the history of the field, their struggles and visions of the future.

By James A. Anderson, Edward Rosenfeld Contributor Edward Rosenfeld Edition: reprint, illustrated Published by MIT Press, 2000 ISBN 0262511118, 9780262511117 448 pages

A second edition of this comprehensive text charts the progress made in recent years in answering the questions 'How does the brain work?' and 'How can we build intelligent machines?' A collection of articles covering modeling realms of neuroscience, cognitive sciences, neural networks and brain theory is presented in alphabetical order by title. Part one covers background, part two, brain theory and neural networks, and part three includes the articles.

By Michael A. Arbib, Shun-ichi Amari, Prudence H. Arbib Edition: 2, illustrated Published by MIT Press, 2003 ISBN 0262011972, 9780262011976 1290 pages