loui@wucs1.wustl.edu (Ron Loui) (11/05/88)
COMPUTER SCIENCE COLLOQUIUM Washington University St. Louis 4 November 1988 TITLE: Why AI needs Connectionism? A Representation and Reasoning Perspective Lokendra Shastri Computer and Information Science Department University of Pennsylvania Any generalized notion of inference is intractable, yet we are capable of drawing a variety of inferences with remarkable efficiency - often in a few hundered milliseconds. These inferences are by no means trivial and support a broad range of cognitive activity such as classifying and recognizing objects, understanding spoken and written language, and performing commonsense reasoning. Any serious attempt at understanding intelligence must provide a detailed computational account of how such inferences may be drawn with requisite efficiency. In this talk we describe some work within the connectionist framework that attempts to offer such an account. We focus on two connectionist knowledge representation and reasoning systems: 1) A connectionist semantic memory that computes optimal solutions to an interesting class of inheritance and recognition problems extremely fast - in time proportional to the depth of the conceptual hierarchy. In addition to being efficient, the connectionist realization is based on an evidential formulation and provides a principled treatment of exceptions, conflicting multiple inheritance, as well as the best-match or partial-match computation. 2) A connectionist system that represents knowledge in terms of multi-place relations (n-ary predicates), and draws a limited class of inferences based on this knowledge with extreme efficiency. The time taken by the system to draw conclusions is proportional to the length of the proof, and hence, optimal. The system incorporates a solution to the "variable binding" problem and uses the temporal dimension to establish and maintain bindings. We conclude that working within the connectionist framework is well motivated as it helps in identifying interesting classes of limited inference that can be performed with extreme efficiently, and aids in discovering constraints that must be placed on the conceptual structure in order to achieve extreme efficiency. host: Ronald Loui ________________________________________________________________________________ 1988-89 AI Colloquium Series (through February) Sep 16 Michael Wellman, MIT/Air Force "The Trade-off Formulation Task in Planning under Uncertainty" 30 Kathryn Laskey, Decision Science Consortium "Assumptions, Beliefs, and Probabilities" Nov 4 Lokendra Shastri, University of Pennsylvania "Why AI Needs Connectionism? A Representation and Reasoning Perspective" 11 Peter Jackson, McDonnell Douglas Research Laboratories "Diagnosis, Defaults, and Abduction" 18 Eric Horvitz, Stanford University (decision-theoretic control of problem-solving) Dec 2 Mark Drummond, NASA Ames (planning) Feb 3 Fahiem Bacchus, University of Waterloo (uncertain reasoning) 10 Dana Nau, University of Maryland (TBA) other speakers to be announced ________________________________________________________________________________