January 2002, Vol. 18, No. 2 Book Shelf Graphical Models : Foundations of Neural Computation, edited by Michael Jordan and Terrence Sejnowski, MIT Press, 421 pp., $32.95, ISBN: 0-262-60042-0 This book exemplifies the interplay between the general formal framework of graphical models and the exploration of new algorithms and architectures. The graphical models framework makes it possible to understand a wide variety of network-based approaches to computation, and in particular to understand many neural network algorithms and architectures as instances of a broader probabilistic methodology. The articles, which are drawn from the journal Neural Computation, range from foundational papers of historical importance to results at the cutting edge of research. Adaptive Image Processing: A Computational Intelligence Perspective, by Ling Guan, Hau-San Wong, Stuart William Perry, Phillip Laplante, CRC Press, 288 pp., $99.95; ISBN: 0849302838 This book examines the problem of adaptive image processing from a viewpoint which is directly linked to human perception. It treats adaptive image processing from a computational intelligence viewpoint, systematically and successfully, from theory to applications, using the synergies of neural networks, fuzzy logic and evolutionary computation. Based on the fundamentals of human perception, this book gives a detailed account of computational intelligence methods and algorithms for adaptive image processing in regularization, edge detection and early vision. Table of Contents Web Site © Copyright 2002 by Lionheart Publishing, Inc. All rights reserved. Lionheart Publishing, Inc. 2555 Cumberland Parkway, Suite 299, Atlanta, GA 30339 USA Phone: 770-431-0867 | Fax: 770-432-6969 E-mail: lpi@lionhrtpub.com Web: www.lionheartpub.com