Parametric tests are only valid if the data satisfy certain assumptions. If these assumptions hold, they will, however, typically give more accurate results. The analysis of statistical learning theory has very much the flavor of a nonparametric statistical test. The weakness of pac, therefore, is that its results must hold true even in worst-case distributions. There is, however, a new twist to this story in that the more recent pacstyle results are able to take account of observed attributes of the function that has been chosen by the learner, for example, its margin on the training set.

Identifying generic, domain-independent tasks, formalizing task representation, elucidating the role of the task in eliciting domain-specific knowledge, and standardizing the design and development of expert systems then became the major research problems of the field. Knowledge specification, includes the task decomposition and the specification of the domain information types and knowledge bases. The task decomposition can be guided by selecting to reuse some of the previously identified task templates. Finally, during knowledge refinement, the models are validated through simulation on paper or with prototyping, and the knowledge bases are refined. Depending on how familiar the analyst is with the domain, these activities might have to be performed repeatedly, and subsequent activities might provide feedback for corrections or extensions to the products of earlier ones.

R B. Abhyankar Emphasizing theory and implementation issues more than specific applications and Prolog programming techniques, Computing with Logic Logic Programming with Prolog (The Benjamin Cummings Publishing Company, Menlo Park, Calif., 1988, 535 pp., $27 95) by David Maier and David S. Warren, respected researchers in logic programming, is a superb book Offering an in-depth treatment of advanced topics, the book also includes the necessary background material on logic and automatic theorem proving, making it self-contained. The only real prerequisite is a first course in data structures, although it would be helpful if the reader has also had a first course in program translation. The book has a wealth of exercises and would make an excellent textbook for advanced undergraduate or graduate students in computer science; it is also appropriate for programmers interested in the implementation of Prolog The book presents the concepts of logic programming using theory presentation, implementation, and application of Proplog, Datalog, and Prolog, three logic programming languages of increasing complexity that are based on horn clause subsets of propositional, predicate, and functional logic, respectively This incremental approach, unique to this book, is effective in conveying a thorough understanding of the subject The book consists of 12 chapters grouped into three parts (Part 1 chapters 1 to 3, Part 2. chapters 4 to 6, and Part 3 chapters 7 to 12), an appendix, and an index The three parts, each dealing with one of these logic programming languages, are organized the same First, the authors informally present the language using examples; an interpreter is also presented. Then the formal syntax and semantics for the language and logic are presented, along with soundness and completeness results for the logic and the effects of various search strategies Next, they give optimization techniques for the interpreter Each chapter ends with exercises, brief comments regarding the material in the chapter, and a bibliography Chapter I presents top-down and bottom-up interpreters for Proplog Chapter 2 offers a good discussion of the related notions: negation as failure, closed-world assumption, minimal models, and stratified programs Chapter 3 considers clause indexing and lazy concatenation as optimization techniques for the Proplog interpreter in chapter 1 Chapter 4 explains the connection between Datalog and relational algebra. Chapter 5 contains a proof of Herbrand's theorem for predicate logic.

It is written with great intelligence and insight and can benefit a wide audience from advanced undergraduates to seasoned researchers. It is a book that should be in the permanent collection of every AI aficionado because it is such a rich source of ideas and examples. It is not a full-blown AI text; it does not depend on the reader having any previous knowledge of AI but does assume some basic knowledge of Lisp. I have used this book with great success as a supplement in an introductory graduate AI course, the text in a graduate AI course focusing on techniques, and a resource in my research group. The sheer amount of material is impressive, including symbolic mathematics, logic programming, natural language, expert systems, games, and more.

Part of the Media Laboratory's heritage (its origins are in the School of Architecture) is a startling receptivity to the arts, especially music and the visual arts, and Brand repeatedly returns to this subject. Even here, intellectualism reigns: It is symptomatic that the lab members' interest in literature seems to be limited to science fiction. This lopsidedness echoes Turkle's complaint that hackers ignore the texture (emotion) of music in favor of its structure (intellect). Not an engineer himself, Brand is not always in a position to critically evaluate what he saw; I was reminded of persons who, on seeing ELIZA, concluded that computerized psychotherapy was just around the corner. As Brand points out, the Media Lab replaces the publish-orperish imperative with demo or die, and anyone who has produced a demo knows something about practical mendacity.

To be considered exceptional, a textbook must satisfy three basic requirements. First, it must be authoritative, written by one with a broad range of experience in, and knowledge of, a subject. Second, it must effectively communicate to the reader, in the same manner in which a course instructor must be capable of imparting knowledge to students in a classroom. Third, it must stimulate the reader into thinking more deeply about the subject and into viewing it from fresh perspectives. In Artificial Intelligence: A Knowledge-Based Approach (Boyd & Fraser, Boston, 740 pp., $48.95), author Morris W. Firebaugh has succeeded in meeting each of these requirements.

If you are interested in writing a review, contact chandra@cis. It is intended to be a "general textbook of knowledge-base analysis and design" (p. Its great strength is recognizing the need for an interdisciplinary approach, and the attempt at presenting the logical and philosophical foundations of knowledge representation under a unified view. Its great weakness is a lack of consistent rigor, which is needed in a textbook for newcomers to a subject. After some historical remarks and a first introductory chapter devoted to logic, Sowa immediately attacks the hard problems involved in choosing ontological categories, which lie at the heart of any knowledge representation project.

The growing field of three-dimensional (3-D) computer vision-programs that can interpret the world from sensor data-is the topic of Three-Dimensional Computer Vision by Yoshiaki Shirai (Springer-Verlag, Berlin, 1987, 297 pp., $95.00) The term "three-dimensional" is used to distinguish the field from two-dimensional pattern (2-D) recognition, such as character recognition or the recognition of silhouettes. The 3-D scene-understanding problem is made difficult by shadows, uneven lighting, texture, and objects that occlude other objects The sensors used include those that obtain a greylevel or color-intensity image of a scene, methods that project a sheet of light on an object to reveal its 3-D structure, and distance-measuring devices that provide a "range image" in which the value of each picture element represents a distance from the sensor to a point in the scene Such range sensors are important because they are not affected by lighting conditions and shadows. This book, not to be confused with Takeo Kanade's Three-Dimensional Machine Vision (Kluwer Academic Publishers, 1987), describes the fundamental technology of 3-D computer vision for various applications The first four chapters are devoted to basic methods of computer vision. This is followed by chapters on image feature extraction (edge analysis, edge linking and following, and region methods) and image feature description (representing lines, segmenting a sequence of points, fitting line equations, and converting between lines and regions). Once these preliminaries are completed, the author concentrates on the 3-D world.

Conceptual Spaces--The Geometry of Thought is a book by Peter Gärdenfors, professor of cognitive science at Lund University, Sweden. Gärdenfors has authored another book in this series (based on work with Carlos Alchourron and David Makinson), Knowledge in Flux, a definitive account of the widely examined AGM (after Alchourron, Gärdenfors, and Makinson) theory of belief revision. The AGM theory is firmly based on classical logic and its model theory, and by his founding participation in developing it, Gärdenfors has earned the right to critique knowledge representation. His new book is not primarily about logic, but it is certainly not an apostasy either. If I may be permitted a minor irreverence, I would say that this book came not to destroy logic but to fulfill.

Judging by the title, I particularly looked forward to information on how artificial intelligence (AI) techniques are or can be employed in psychiatric analysis, diagnosis, and management of patients or disorders. Upon reading Hand's preface, my hopes turned to enthusiasm. According to the author, the goals of the book are to "outline Artificial Intelligence methods in a way which is intelligible to psychiatrists (and to others] with no knowledge of computers" and to relate AI to psychiatry in general. Although the first goal meant reviewing familiar material, the second objective was certain to make reading the entire book a worthwhile effort. After all, I reasoned, some point might well be implied in the selection of material and its order of presentation.