The Association for the Advancement of Artificial Intelligence held its 1995 Spring Symposium Series on March 27 to 29 at Stanford University. This article contains summaries of the nine symposia that were conducted: (1) Empirical Methods in Discourse Interpretation and Generation; (2) Extending Theories of Action: Formal Theory and Practical Applications; (3) Information Gathering from Heterogeneous, Distributed Environments; (4) Integrated Planning Applications; (5) Interactive Story Systems: Plot and Character; (6) Lessons Learned from Implemented Software Architectures for Physical Agents; (7) Representation and Acquisition of Lexical Knowledge: Polysemy, Ambiguity, and Generativity; (8) Representing Mental States and Mechanisms; and (9) Systematic Methods of Scientific Discovery.

Analogy has a rich history in Western civilization. Over the centuries, it has become reified in that analogical reasoning has sometimes been regarded as a fundamental cognitive process. In addition, it has become identified with a particular expressive format. The limitations of the modern view are illustrated by monster analogies, which show that analogy need not be regarded as something having a single form, format, or semantics. Analogy clearly does depend on the human ability to create and use well-defined or analytic formats for laying out propositions that express or imply meanings and perceptions. Beyond this dependence, research in cognitive science suggests that analogy relies on a number of genuinely fundamental cognitive capabilities, including semantic flexibility, the perception of resemblances and of distinctions, imagination, and metaphor. Extant symbolic models of analogical reasoning have various sorts of limitation, yet each model presents some important insights and plausible mechanisms. I argue that future efforts could be aimed at integration. This aim would include the incorporation of contextual information, the construction of semantic bases that are dynamic and knowledge rich, and the incorporation of multiple approaches to the problems of inference constraint.

Model of Mental Fluidity and Analogy Making," is perhaps the best The representation is then elaborated by many codelets, small pieces of code that do specific things. Some codelets recognize potential structures but do Fluid Concepts and Creative Analogies, Dave Chalmers, Daniel Defays, Bob not build them; others build structures Douglas Hofstadter and the French, Gary McGraw, and Melanie that have been identified. Because of the parallelism, competing whole book, reinforced by the prefaces structures can be built; other Hofstadter wrote for each article. The structure these ideas are related, one is primarily the Carl Sagan of AI. A parallel terraced scan is similar a constant interaction between how based on irrelevancies. Chapter 4, to see some attempt to learn is a collection of articles, many "High-Level Perception, Representation, codelets using genetic algorithms.

My collaborators and I have recently reported in domain science journals several human-computer discoveries in biology, chemistry, and physics. One might ask what accounts for these findings, for example, whether they share a common pattern. My conclusion is that each finding involves a new representation of the scientific task: The problem spaces searched were unlike previous task problem spaces. Such new representations need not be wholly new to the history of science; rather, they can draw on useful representational pieces from elsewhere in natural or computer science. This account contrasts with earlier explanations of machine discovery based on the expert system view. My analysis also suggests a broader potential role for (AI) computer scientists in the practice of natural science.

Prizes were awarded to students to encourage improved research. Michel Wermelinger, Universidade Nova de Lisboa, Portugal, was the winner of the best paper award for his work "Basic Conceptual Structure Theory," which provided a significant In "Representations Technology, Bangkok, Thailand, won Papers were presented by a number interest in the use of conceptual he Second International Conference (ICCS'94) was held at the of individuals and groups from graphs. The funds were made available University of Maryland, College several countries on the development through a grant from the American Park, Maryland, on August 16 to 20. and use of the conceptual Association for Artificial Intelligence The conference marked the tenth graph representational language. Sponsors included the University of Graph Workbench," chaired by Gerard vice-president of academic affairs, Paradigm Development Corp. in Urbana, Illinois, was the second She received her Ph.D. from the introduction, "Aristotelian and

This report stems from a workshop that was organized by the Association for the Advancement of Artificial Intelligence (AAAI) and cosponsored by the Information Technology and Organizations Program of the National Science Foundation. The purpose of the workshop was twofold: first, to increase awareness among the artificial intelligence (AI) community of opportunities presented by the National Information Infrastructure (NII) activities, in particular, the Information Infrastructure and Tech-nology Applications (IITA) component of the High Performance Computing and Communications Program; and second, to identify key contributions of research in AI to the NII and IITA.

The Swiss Bank, one of the largest A team that includes AI Ware (Cleveland, develop a new computer telephone banks based in Switzerland, has Ohio), a vendor of intelligent integration solution, based on speech reached an agreement with virtual systems for design and manufacturing recognition for the PC. Users will be reality tool developer Sense8 (Mill applications, has been awarded a $3.8 Valley, Calif.) to integrate Sense8's able to access important information million grant by the National Institute The GUI will allow users to access and of location. Gensym (Cambridge, Mass.), supplier Calif.) has been awarded a $1 million with self-improving capabilities Contact locations, Motorola plans to Communications Corp. (Mountain Lionheart Publishing Inc., 2555 deploy virtual worlds for on-site training View, Calif.), a provider of open software Cumberland Parkway, Suite 299, at plants around the world. A computer-based vision system has Engine it its Netscape servers. Topic been developed that reportedly can Mitek Systems (San Diego, Calif.), a Agents allow users and online identify faces as accurately as the manufacturer of advanced character providers to filter incoming information human eye, even to the point of seeing recognition products for intelligent against interest profiles and send past most disguises.

Several of the workshops have led to discourse? At what levels of the art in the field (Dale et al. 1992; generation is information processed on Natural Language Paris, Swartout, and Mann 1991; How can we generate to 24 June 1994 at the Nonantum The goal of this latest workshop multilingual texts efficiently? Inn on the seacoast in Kennebunkport, was to introduce new, cutting-edge The topics presented at the workshop Maine. Two invited speakers described subtopics such as evaluation, casual site contributed greatly to their perspectives on two areas outside explanation generation, and summarization the success of the workshop in stimulating the field that might become an occur with increasing frequency the exchange of ideas. Pustejovsky (Brandeis University) presented Different generator designers make that any individual generation his views on the richness of different choices, and the resulting project should define--in its own what can be encoded in what he calls systems are hard to compare.

This book review examines Artificial Intelligence: A Modern Approach, by Stuart Russell and Peter Norvig, Prentice Hall, Englewood Cliffs, New Jersey, 1995, 932 pp., $62.90, ISBN 0-13-103805-2.

Learning and reasoning are both aspects of what is considered to be intelligence. Their studies within AI have been separated historically, learning being the topic of machine learning and neural networks, and reasoning falling under classical (or symbolic) AI. However, learning and reasoning are in many ways interdependent. This paper discusses the nature of some of these interdependencies and proposes a general framework called FLARE, that combines inductive learning using prior knowledge together with reasoning in a propositional setting. Several examples that test the framework are presented, including classical induction, many important reasoning protocols and two simple expert systems.