clarke@utcsri.UUCP (Jim Clarke) (09/01/85)
(SF = Sandford Fleming Building, 10 King's College Road) (GB = Galbraith Building, 35 St. George) COLLOQUIUM, Tuesday, September 10, 11 am, SF1105 Dr. Sidney E. Harris Decision Sciences Laboratory Georgia State University "Models of Unstructured Office Activity" Models of office activities have been primarily oriented towards office work that is structured and organized. However, the design of office information systems to match human cognitive processes is becoming increasingly important as systems become more sophisticated. In this presentation, some empirical results and models of unstructured office activity will be reviewed. Emphasis will be placed on problem-solving and document preparation applications and the way in which models can facili- tate needs assessment evaluation. ARTIFICIAL INTELLIGENCE SEMINAR, Tuesday, September 10, 3 pm, SF1105 Professor David Touretzky Carnegie-Mellon University "Symbols among the Neurons: Details of a Connectionist Inference Architecture" Pattern matching and variable binding are easily implemented in con- ventional computer architectures, but not necessarily in all architectures. In a distributed neural network architecture each symbol is represented by activity in many units and each unit contributes to the representation of many symbols. Manipulating symbols using this type of distributed representation is not as easy as with a local representation where each unit denotes one symbol, but there is evidence that the distributed approach is the one chosen by nature. We describe a working implementation of a production system interpreter in a neural network using distributed representations for both symbols and rules. The research provides a detailed account of two important symbolic reasoning operations, pattern matching and variable binding, as emergent properties of collections of neuron-like elements. The success of our production system implementation goes some way towards answering a common criticism of connectionist theories: that they aren't powerful enough to do symbolic reasoning. ARTIFICIAL INTELLIGENCE SEMINAR, Thursday, September 12, 11 am., SF1105 Professor Veronica Dahl Simon Fraser University "Gapping Grammars for Natural Language Analysis" COMPUTER ALGEBRA SEMINAR, Thursday, September 12, 4 pm., GB414 Scott McCallum DCS, University of Toronto "Survey of Computer Algebra" -- Jim Clarke -- Dept. of Computer Science, Univ. of Toronto, Canada M5S 1A4 (416) 978-4058 {allegra,cornell,decvax,ihnp4,linus,utzoo}!utcsri!clarke