Advances in computer hardware and software and engineering methodologies in the 1960s and 1970s led to an increased use of computers by engineers. In design, this use has been limited almost exclusively to algorithmic solutions such as finite-element methods and circuit simulators. However, a number of problems encountered in design are not amenable to purely algorithmic solutions. These problems are often ill structured (the term ill-structured problems is used here to denote problems that do not have a clearly defined algorithmic solution), and an experienced engineer deals with them using judgment and experience. AI techniques, in particular the knowledge-based system (KBS) technology, offer a methodology to solve these ill-structured design problems. In this article, we describe several research projects that utilize KBS techniques for design automation. These projects are (1) the Criteria Yielding, Consistent Labeling with Optimization and Precedents-Based System (CYCLOPS), which generates innovative designs by using a three-stage process: normal search, exploration, and adaptation; (2) the Concept Generator (CONGEN), which is a domain independent framework for conceptual or preliminary design; (3) Constraint Manager (CONMAN), which is a constraint-management system that performs the evaluation and consistency maintenance of constraints arising in design; (4) the distributed and integrated environment for computer-aided engineering (DICE), which facilitates coordination, communication, and control during the entire design and construction/manu-facturing phases; and (5) DESIGN-KIT, which can be envisioned as a new generation of computer-aided engineering environment for process-engineering applications.

To read the book "Automated Reasoning: Thirty-Three Basic Research problems (Prentice Hall, Englewood Cliffs, N.J., 1987, 300 pp., $11.00) by Larry Was it is not necessary to be an expert in mathematics or logic or computer science. However, even if you are such an expert, you will read it with interest, and likely, with enjoyment.

Commonsense reasoning about the physical world, as exemplified by "Iron sinks in water" or "If a ball is dropped it gains speed," will be indispensable in future programs. We argue that to make such predictions (namely, envisioning), programs should use abstract entities (such as the gravitational field), principles (such as the principle of superposition), and laws (such as the conservation of energy) of physics for representation and reasoning. These arguments are in accord with a recent study in physics instruction where expert problem solving is related to the construction of physical representations that contain fictitious, imagined entities such as forces and momenta (Larkin 1983). We give several examples showing the power of physical representations.

McDermott makes some valid points in his review ... It's too bad that he chose to embed the helpful comments in the context of his by-now-tiresome doubts about the value of logic in AI.

The book "Logical Foundations of Artificial Intelligence (Morgan Kaufmann, Los Altos, Calif., 1987, 406 pp., $48.95) by Michael Genesereth and Nils Nilsson is about declarative knowledge.

Commentators on AI converge on two goals they believe define the field: (1) to better understand the mind by specifying computational models and (2) to construct computer systems that perform actions traditionally regarded as mental. We should recognize that AI has a third, hidden, more basic aim; that the first two goals are special cases of the third; and that the actual technical substance of AI concerns only this more basic aim. This third aim is to establish new computation-based representational media, media in which human intellect can come to express itself with different clarity and force. This article articulates this proposal by showing how the intellectual activity we label AI can be likened in revealing ways to each of five familiar technologies.

Over the last eight years, four workshops on machine learning have been held. Participation in these workshops was by invitation only. In response to the rapid growth in the number of researchers active in machine learning, it was decided that the fifth meeting should be a conference with open attendance and full review for presented papers. Thus, the first open conference on machine learning took place 12 to 14 June 1988 at The University of Michigan at Ann Arbor.

It is important material, but it by a main text that consists mostly of belongs earlier in the book. I feel the Robert A. Chalmers engaging narratives about how some lack of a strong positive closing, the The authors of The Rise

A panel session at the 1989 International Joint Conference on Artificial Intelligence in Los Angeles dealt with the subject of knowledge-based systems; the session was entitled "Expert Systems: How Far Can They Go?" The panelists included Randall Davis (Massachusetts Institute of Technology); Stuart Dreyfus (University of California at Berkeley); Brian Smith (Xerox Palo Alto Research Center); and Terry Winograd (Stanford University), chairman. Part 1 of this article, which appeared in the Spring 1989 issue, began with Winograd's original charge to the panel, followed by lightly edited transcripts of presentations from Winograd and Dreyfus. Part 2 begins with the presentations from Smith and Davis and concludes with the panel discussion. Although almost four years have passed since this discussion took place, the issues raised and the points discussed appear no less relevant today.

Having been involved in there is a page limit on the papers.