A fundamental question in AI is what mechanisms suffice for computer programs to make scientific discoveries. My Ph.D. thesis addresses this question by automating the following scientific task to a significant extent: Given observed data about a particular chemical reaction, discover the underlying set of reaction steps from starting materials to products, that is, elucidate the reaction pathway.

Bratman's definition of intention is papers range from philosophical This review is organized around the jumping-off point for Cohen and analyses of the concept of intention three of the themes that are sounded Levesque's two papers: "Persistence, to algorithms for recognizing plans, in Intentions in Communication: (1) Intention, and Commitment" and from logical formalizations of speech foundational work on intention and "Rational Interaction as the Basis of acts to analyses of intonational contours its relation to speech act theory, (2) Communication."

The AAAI-90 Workshop on Qualitative Vision was held on Sunday, 29 July 1990. Over 50 researchers from North America, Europe, and Japan attended the workshop. This article contains a report of the workshop presentations and discussions.

Each of the The second volume promises to inherent to the task of specifying objections is then analyzed from a draw on a characterization of AI's the deterministic or nondeterministic formal standpoint because the relevant essential methodology as continuous machine, and complexity of electric elements of formal theory are attempts to overcome the formal or logical circuits), physical limits of introduced in subsequent chapters. I hope to see my (that is, finite, discrete concepts can Lovelace's objection. Despite the criticisms dissipate after reading the never form a perfect model of a continuous introductory character of the chapter, second volume. Let's get a feeling of what this first and possible-world semantics. With volume is really about.

I give an introduction to Bayesian networks for AI researchers with a limited grounding in probability theory. Over the last few years, this method of reasoning using probabilities has become popular within the AI probability and uncertainty community. Indeed, it is probably fair to say that Bayesian networks are to a large segment of the AI-uncertainty community what resolution theorem proving is to the AIlogic community. Nevertheless, despite what seems to be their obvious importance, the ideas and techniques have not spread much beyond the research community responsible for them. This is probably because the ideas and techniques are not that easy to understand. I hope to rectify this situation by making Bayesian networks more accessible to the probabilistically unsophisticated.

Based Analysis of Indirect Speech Acts.

Geneva1 Because of electrical interference Object classification is possible using three Things in the environment will consist of between robots, none of the competition kinds of sensors Parts of the scoring use an "naturally ocurring" items in the exhibition olympic-style judging The over-arching

The Association for the Advancement of Artificial Intelligence held its 1991 Spring Symposium Series on March 26-28 at Stanford University, Stanford, California. This article contains short summaries of the eight symposia that were conducted: Argumentation and Belief, Composite System Design, Connectionist Natural Language Processing, Constraint-Based Reasoning, Implemented Knowledge Representation and Reasoning Systems, Integrated Intelligent Architectures, Logical Formalizations of Commonsense Reasoning, and Machine Learning of Natural Language and Ontology.

I survey four viewpoints about what AI is. I describe a program exhibiting AI as one that can change as a result of interactions with the user. Such a program would have to process hundreds or thousands of examples as opposed to a handful. Because AI is a machine's attempt to explain the behavior of the (human) system it is trying to model, the ability of a program design to scale up is critical. Researchers need to face the complexities of scaling up to programs that actually serve a purpose. The move from toy domains into concrete ones has three big consequences for the development of AI. First, it will force software designers to face the idiosyncrasies of its users. Second, it will act as an important reality check between the language of the machine, the software, and the user. Third, the scaled-up programs will become templates for future work. For a variety of reasons, some of which I discuss one of the following four things: (1) AI means in this article, the newly formed Institute magic bullets, (2) AI means inference engines, for the Learning Sciences has been concentrating (3) AI means getting a machine to do something its efforts on building high-quality you didn't think a machine could do educational software for use in business and (the "gee whiz" view), and (4) AI means elementary and secondary schools. In the two having a machine learn.

Automated diagnosis is an important AI problem not only for its potential practical applications but also because it exposes issues common to all automated reasoning efforts and presents real challenges to existing paradigms. Current research in this area addresses many problems, including managing and structuring probabilistic information, modeling physical systems, reasoning with defeasible assumptions, and interleaving deliberation and action. Furthermore, diagnosis programs must face these problems in contexts where scaling up to deal with cases of realistic size results in daunting combinatorics. This article presents these and other issues as discussed at the First International Workshop on Principles of Diagnosis.