Keynote Speakers
Keynote SpeakersA number of emminent and influential speakers have been invited to present keynote papers. Below are their biographical details and abstracts of their talks.
Last modified Fri Oct 6 11:29:14 1995
Is Computational Intelligence really different from AI?
This talk is about three kinds of intelligence: biological, artificial and computational. The talk is framed in the context of pattern recognition in general, and neural networks in particular. I will argue that artificial intelligence (AI) has a much broader scope than computational intelligence (CI); and further, that neural networks are but one facet of computational intelligence. I will illustrate my thesis with examples of low, mid and high level aspirations towards intelligent behaviour.
Jim Bezdek received the BSCE from the University of Nevada (Reno) in 1969, and the Ph.D. in Applied Math from Cornell in 1973. He is currently a Professor in the Computer Science Department at the University of West. Florida . His previous experience includes the directorship of Boeing's HTC Inf. Proc. Lab, and a term as head of Computer Science at the University of South Carolina.
Jim's interests include optimization, motorcycles, pattern recognition, fishing, vision and image processing, skiing, computational neural networks, blues music, and medical applications . Jim is the founding editor of the Int'l. Jo. Approximate Reasoning and the IEEE Transactions on Fuzzy Systems. He is a distinguished lecturer for the IEEE and ACM and is an IEEE fellow. He is currently on a sebatical at the University of Western Australia as the Gledden Senior Visiting Fellow.
Interactive coordination processes: how the brain accomplishes what we take for granted in computer languages --- and then does it better.
William J. Clancey is a Senior Research Scientist at the Institute for Research on Learning. He received a PhD in Computer Science at Stanford University in 1979, after graduating Summa Cum Laude in Mathematical Sciences (BA) from Rice University in 1974.
Involved in expert systems research at Stanford from the early days of the MYCIN Project in 1975, Clancey developed some of the earliest AI programs for explanation, the critiquing method of consultation, tutorial discourse, student modeling, and failure-driven learning. His interests during the 1980s included using expert systems for teaching and relating AI programming to traditional scientific and engineering modeling.
Clancey's programming methods separate a systems model from the inference strategy for specific tasks such as design and diagnosis, realized in the expert system NEOMYCIN and the first "generic expert system shell," HERACLES. His analyses of qualitative modeling have had significant effect on the design of expert systems and instructional programs, formalized in a series of papers including:
In addition to fifteen journal articles, nineteen book chapters, eighteen conference papers and technical reports, and six book reviews, Clancey has published four books:
Clancey has presented tutorials and keynote addresses in eleven countries. His recent publications re-examine the relation of cognitive science theories to the processes of human memory and learning. He is Editor-in-Chief of The AAAI Press and serves on several editorial boards, including Artificial Intelligence. He is a Senior Editor of Cognitive Science. Clancey also has experience in the practical application of AI technology as a co-founder of Teknowledge Inc.(1981) and founder and member of the Board of Directors of ModernSoft, Inc. (1989). Clancey received Patent No. 4847784 for "Knowledge-Based Tutor," a design for interactive, case-based probing relevant to both teaching and knowledge acquisition.
Evolving intelligence.
The symbolic/subsymbolic distinction between approaches to AI has been with us for a long time. In this paper I argue that it no longer serves a useful purpose, and that we need to focus on multi-faceted approaches to AI. I suggest that evolutionary algorithms have considerable potential for the design of such systems, and I provide some examples of work in progress. I note that there are signs that we are reaching the limits of our ability to hand-construct complex AI systems and that we need to seriously consider evolving intelligence.
Kenneth A. De Jong received his Ph.D. in computer science from the University of Michigan in 1975. He joined George Mason University in 1984 and is currently Associate Professor of Computer Science. His research interests include genetic algorithms, evolutionary computation, machine learning, and adaptive systems. He is currently involved in research projects involving the development of new genetic algorithm (GA) theory, the use of GAs as heuristics for NP-hard problems, and the application of GAs to the problem of learning task programs in domains such as robotics, diagnostics, navigation and game playing. He is also interested in experience-based learning in which systems must improve their performance while actually performing the desired tasks in environments not directly their control or the control of a benevolent teacher. Support for these projects is provided by DARPA, ONR, and NRL. He is an active member of the GA research community and has been involved in organising many of the workshops and conferences in this area. He is the currently the editor-in-chief of the journal Evolutionary Computing, and a member of the editorial board of the Machine Learning journal.
Observing the Universe Can Drown You in Images: Machine Learning Solutions at JPL.
Usama Fayyad is Technical Group Supervisor of the Machine Learning Systems Group at the Jet Propulsion Laboratory, California Institute of Technology. He is also an adjunct assistant professor in the CS Dept. at USC. At JPL, he is Principal Investigator of the Science Data Analysis and Visualization Task targeting applications of data mining techniques for the analysis of large science databases, as well as other tasks involving industrial applications of machine learning. He received the Ph.D. degree in Computer Science and Engineering in 1991 from the EECS Department of The University of Michigan, Ann Arbor. He holds the following degrees: B.S.E. in E.E., B.S.E. and M.S.E. in Computer Engin., and M.Sc. in Mathematics. He is a recepient of the 1993 Lew Allen Award for Excellence, the highest honor JPL awards to researchers in the early years of their professional careers. He has also received the NASA Exceptional Achievement Medal (1994). His research interests include machine learning theory and applications, knowledge discovery in large databases, data mining, statistical pattern recognition, clustering, and non-linear regression. He served on the program committees of several conferences in AI including AAAI-93, ML-93+95, TAI-93. He has co-chaired the Eleventh SPIE Applications of AI Conference (1993), and the 1994 Knowledge Discovery in Databases Workshop at AAAI-94. He is co-chair of the First International Conference on Knowedge Discovery and Data Mining (KDD-95), and co-editor of the book: "Advances in Knowledge Discovery and Data Mining", published by AAAI/MIT Press (1995).
Negotiating the Neural Network Obstacle Course
Dr. Susan Garavagli, Asistant Vice President in the Analytical Services Group, Dun & Bradstreet, is experienced in a variety of decision support applications, including client prospecting, creditworthiness evaluation, data classiffication, and fraud detection. She specializes in using neural network and other artificial intelligence technologies as well as traditional econometric methods. In addition, she has over twenty-three years of experience in all aspects of computer systems implementation.
Prior to joining Dun & Bradstreet, she was a Vice President at Chase Manhattan Bank, where she was manager of AI and Special Projects in the bank's Corporate Finance unit. At Chase she also introduced AI technology into many of the bank's business units. In addition, she had her own consulting practice for six years and, earlier, held advanced technology positions at Manufacturers Hanover Trust Company and Metropolitan Life Insurance.
Susan also has published papers and given presentations and tutorials on neural network technology. Several chapters of her dissertation, "Economic Rationality and Neural Networks" have been presented at conferences.
Susan's undergraduate degree is a Bachelor of Music in Composition from the Juilliard School. Her M.B.A. is in Finance and Investments from Baruch College and she received her Ph.D. in economics from City Univeristy of New York Graduate Center