Chandrasekaran, Balakrishnan


Review of Intelligent Systems for Engineering: A Knowledge-Based Approach

AI Magazine

Review of Intelligent Systems for Engineering: A Knowledge-Based Approach, Ram D. Sriram, Springer Verlag, 804 pp., 1997, ISBN 3-540-76128-4.


A Message to Readers

AI Magazine

A few weeks after my appointment as Book Reviews editor, I started receiving a large number of books from AAAI, books that have been accumulating since the last reviewer stepped down. As I was going through them, I thought, "So many books, so few pages." AI Magazine is not a publication exclusively devoted to books, such as the New York Review or the weekly book review supplements of major newspapers. At best, it can devote a few pages each issue to book reviews. Also, it doesn't appear that frequently, just four issues a year. Given these constraints, how can the magazine best serve its readership?


A Review of Sketches of Thought

AI Magazine

Review of "Sketches of Thought, Vinod Goel, The MIT Press, Cambridge, Massachusetts, 1995, 279 pp., ISBN 0-262-07163-0.


Reasoning with Diagrammatic Representations: A Report on the Spring Symposium

AI Magazine

We report on the spring 1992 symposium on diagrammatic representations in reasoning and problem solving sponsored by the Association for the Advancement of Artificial Intelligence. The symposium brought together psychologists, computer scientists, and philosophers to discuss a range of issues covering both externally represented diagrams and mental images and both psychology -- and AI-related issues. In this article, we develop a framework for thinking about the issues that were the focus of the symposium as well as report on the discussions that took place. We anticipate that traditional symbolic representations will increasingly be combined with iconic representations in future AI research and technology and that this symposium is simply the first of many that will be devoted to this topic.


Reasoning with Diagrammatic Representations: A Report on the Spring Symposium

AI Magazine

We report on the spring 1992 symposium on diagrammatic representations in reasoning and problem solving sponsored by the Association for the Advancement of Artificial Intelligence. The symposium brought together psychologists, computer scientists, and philosophers to discuss a range of issues covering both externally represented diagrams and mental images and both psychology -- and AI-related issues. In this article, we develop a framework for thinking about the issues that were the focus of the symposium as well as report on the discussions that took place. We anticipate that traditional symbolic representations will increasingly be combined with iconic representations in future AI research and technology and that this symposium is simply the first of many that will be devoted to this topic.


Design Problem Solving: A Task Analysis

AI Magazine

I propose a task structure for design by analyzing a general class of methods that I call propose-critique-modify methods. The task structure is constructed by identifying a range of methods for each task. This recursive style of analysis provides a framework in which we can understand a number of particular proposals for design problem solving as specific combinations of tasks, methods, and subtasks. The analysis shows that there is no one ideal method for design, and good design problem solving is a result of recursively selecting methods based on a number of criteria, including knowledge availability.


Design Problem Solving: A Task Analysis

AI Magazine

I propose a task structure for design by analyzing a general class of methods that I call propose-critique-modify methods. The task structure is constructed by identifying a range of methods for each task. For each method, the knowledge needed and the subtasks that it sets up are identified. This recursive style of analysis provides a framework in which we can understand a number of particular proposals for design problem solving as specific combinations of tasks, methods, and subtasks. Most of the subtasks are not really specific to design as such. The analysis shows that there is no one ideal method for design, and good design problem solving is a result of recursively selecting methods based on a number of criteria, including knowledge availability. How the task analysis can help in knowledge acquisition and system design is discussed.


Theoretical Issues in Conceptual Information Processing

AI Magazine

The Fifth Annual Theoretical Issues in Conceptual Information Processing Workshop took place in Washington, D.C. in June 1987. About 100 participants gathered to hear several invited talks and panels discussing the issues relating to artificial intelligence and cognitive science.


Connectionism and Information Processing Abstractions

AI Magazine

Connectionism challenges a basic assumption of much of AI, that mental processes are best viewed as algorithmic symbol manipulations. Connectionism replaces symbol structures with distributed representations in the form of weights between units. For problems close to the architecture of the underlying machines, connectionist and symbolic approaches can make different representational commitments for a task and, thus, can constitute different theories. The connectionist hope of using learning to obviate explicit specification of this content is undermined by the problem of programming appropriate initial connectionist architectures so that they can in fact learn.


Theoretical Issues in Conceptual Information Processing

AI Magazine

The Fifth Annual Theoretical Issues in Conceptual Information Processing Workshop took place in Washington, D.C. in June 1987. About 100 participants gathered to hear several invited talks and panels discussing the issues relating to artificial intelligence and cognitive science.