Review of The Mind Doesn't Work That Way: The Scope and Limits of Computational Psychology If you are interested in writing a review, contact chandra@ cis.ohio-state.edu. AT question: Which one of the following doesn't belong with the rest? It is the only discipline in the list that is not under attack for being conceptually or methodologically confused. Objections to AI and computational cognitive science are myriad. Accordingly, there are many different reasons for these attacks. However, all of them come down to one simple observation: Humans seem a lot smarter than computers--not just smarter as in Einstein was smarter than I, or I am smarter than a chimpanzee, but more like I am smarter than a pencil sharpener. To many, computation seems like the wrong paradigm for studying the mind. All this is because of another truth: The computational paradigm is the best thing to come down the pike since the wheel. The Mind Doesn't Work That Way: The Scope and Limits of Computational Psychology, Jerry Fodor, Cambridge, Massachusetts, The MIT Press, 2000, 126 pages, $22.95. Jerry Fodor believes this latter claim. He says: [The computational theory of mind] is, in my view, by far the best theory of cognition that we've got; indeed, the only one we've got that's worth the bother of a serious discussion.… There is, in short, every reason to suppose that Computational Theory is part of the truth about cognition. It is a fascinating read. This dispute about quantity of truth is where the book gets its title. In 1997, Steven Pinker published an important book describing the current state of the art in cognitive science (see also Plotkin [1997]). Pinker's book is entitled How the Mind Works. In it, he describes how computationalism, psychological nativism (the idea that many of our concepts are innate), massive modularity (the idea that most mental processes occur within a domain-specific, encapsulated specialpurpose processor), and Darwinian adaptationism combine to form a robust (but nascent) theory of mind. Fodor, however, thinks that the mind doesn't work that way or, anyhow, not very much of the mind works that way. Fodor dubs the synthesis of computationalism, nativism, massive modularity, and adaptationism the new synthesis (p.

Designing Expert Systems relate expert system research to that findings are abstracted into problem categories (they call them only "intermediate hypotheses") or that hypotheses are refined into subtypes (they say that hypotheses can be organized in a taxonomy, but give no examples). Most importantly, they miss the idea that expert systems often solve a sequence of problems by classification. Common examples are: making a diagnosis and then selecting a repair, characterizing a patient stereotypically and matching this to diseases, and modeling a user's needs and satisfying them (see (Clancey, 1984) for further discussion). Beyond this, Weiss and Kulikowski perpetuate the confusion that classification is a property of problems, rather than a problem solving method. Diagnosis is not inherently a "classification problem."

Mind, that is based on a new television series shown on BBC, but not yet in America. The book is a very well edited transcription of fifteen interviews with psychologists, anthropologists, and sociologists, including such n,otables as George Miller, Jerome Bruner, and Rom Harre. The contributors probably familiar to most AI researchers are Daniel Dennett and Jerome Fodor, as well as two contributors well-known for their writing on art and perception, Ernst Gombrich and Richard Gregory. The interviews are uniformly intelligent, original, and stimulating. As summaries of basic arguments about mental models, perception, and ethical questions of mental problems, you can't do better than this collection.

Intelligent Scheduling is a system-oriented book on scheduling systems. Each chapter describes a scheduling system in terms of the particular scheduling problems being addressed, design assumptions, and the overall paradigm being used. The book is divided into two sections: (1) scheduling methodologies and (2) application case studies. The methodology chapters focus on research systems and scheduling techniques. The application chapters focus on fielded embedded scheduling systems and describe difficulties and lessons learned.

Stephen Grossberg The expanded edition of Perceptrons (MIT Press, Cambridge, Mass, 1988, 292 pp, $12.50) by Marvin L. Minsky and Seymour A. Papert comes at a time of unprecedented interest in the biological and technological modeling of neural networks. The one-year-old International Neural Network Society (INNS) already has over 3500 members from 38 countries and 49 U.S. states, with members joining at the rate of more than 200 per month. The American Association for Artificial Intelligence was, in fact, a cooperating society at the INNS First Annual Meeting in Boston on 6-10 September 1988. Hardly a week goes by in which a scientific meeting or special journal issue does not feature recent neural network research. Thus, substantive technical reviews or informed general assessments of the broad sweep of neural network research are most welcome to help interested scientists find their way into this rapidly evolving technology.

Because of the emphasis on the specifics in each field rather than the general principles involved, the relationship between AI and the subjects under discussion is unclear. Some topics, such as Teitelman's algorithm for recognizing handwritten characters, were extremely difficult to decipher. The appropriateness of including such in-depth treatments in an introductory text on AI is questionable. Thankfully, Firebaugh reverts to his more characteristic style with the subsequent chapter on machine learning. Here is a highly focused discussion; the concepts, applications, and relative merits of various machine learning techniques and their relationship to AI are neatly presented.

The idea is that although an AI system without the frame problem might, say, read an echocardiogram and diagnose a heart defect, a really smart autonomous robot will arrive only if, like us humans, it can handle the frame problem. The highlight … is an entertaining go-round between two pugilists trading blows in civil but gloves-off style, reminiscent of a net discussion. We're still confronted by a difficult question: Is there a solution to it? If not, then R2D2 might forever be but a creature of fiction. If, however, the frame problem is solvable, we must confront yet another question: Is there a general solution to the frame problem, or is the best that can be mustered a so-called domain-dependent solution?

The two-volume set entitled Knowledge-Based Systems (Volume 1, Knowledge Acquisition for Knowledge-Based Systems, 355 pp., and Volume 2, Knowledge Acquisition Tools for Expert Systems, 343 pp., Academic Press, San Diego, California, 1988), edited by B. R. Gaines and J. H. Boose, is an excellent collection of papers useful to both commercial practitioners of knowledge-based-systems development and research-oriented scientists at specialized centers or academic institutions. The set is the result of a call for papers to support the first American Association for Artificial Intelligence Knowledge Acquisition for Knowledge-Based Systems Workshop, held 3-7 November 1986 in Banff, Canada. Although the conference was held three years ago, these volumes are still timely and sorely needed. Few books dedicated to knowledge acquisition exist. The first volume, Knowledge Acquisition for Knowledge-Based Systems, begins with a paper whose title sounds appropriate: "An Overview of Knowledge Acquisition and Transfer" by the editor B. R. Gaines.

AI Magazine Volume 9 Number 3 (1988) ( AAAI) The first part of the book is intended to be an introduction to computational jurisprudence for both groups. It identifies issues critical to the purpose, behavior, knowledge sources, knowledge structures, and reasoning processes of expert legal systems. The second part implements a simple prototype system for a well-defined area of contract law and is more appropriate for experienced developers of knowledge-based systems. Law is a domain in which the experts are supposed to disagree, and lawyers must be able to argue either side of a case. A judge or juror must decide which argument is "best."

The Japanese Fif-t,h Generation Project appears to be only a stimulus for this book. Clearly it is an important stimulus, and the book describes it in considerable detail as it covers both technical and managerial/social aspects of the Japanese project. But the book goes much beyond a description and an evaluation of the Fifth Generation Project In building the background of the project's significance, the book describes the current state of work in artificial intelligence (AI) in the US and abroad, it outlines the history of AI, it, focuses on developments in Expert Systems, it comments on the social and political environment in which AI is growing, and it provides glimpses of the type of future that AI may help us to create. Also, the relative state of industrial development in Japan and t,he US are analyzed, and many observations are made about styles of planning, value systems, and attitudes to education in the two countries. The book conveys very well the sense of intellectual excitement that characterizes work in AI, and the variety of viewpoints (and concerns) within the field about the possible impact on our lives of mass-produced knowledge technology.