|
|
|
Tutorials
Wednesday, July 25, 2001
IFSA/NAFIPS 2001 will feature a series of tutorials by internationally recognized authorities from universities and business. All tutorials will be held in the conference center of the Coast Plaza and Suites Hotel at Stanley Park. The fee for participating in a tutorial is US$125. Tutorial reservations may be sent with the Conference Registration Form (registration information can be found at
Conference Registration), or contact:
IFSA/NAFIPS 201
Venue West Conference Services, Ltd.
645-375 Water St.
Vancouver, BC V6B 5C6 Canada
Tel: +1-604-681-5226
Fax: +1-604-681-2503
e-mail: congress@venuewest.com
Office hours: 0830-1700 Monday - Friday
The DEADLINE for receipt of the tutorial fee by Venue West Conference Services is May 25, 2001. Attendees are encouraged to make their reservations early.
Tutorial WA1
Computing with Words and its Applications
08:30-12:30 July 25, 2001
Lotfi A. Zadeh
University of California at Berkeley
USA
Abstract:
Computing with words (CW) is an evolving methodology based on fuzzy logic-- a methodology which is likely to become a widely used tool, with applications ranging from search and deduction in the Internet to decision-making in an environment of imprecision, uncertainty and partial truth.
A concept which plays a key role in computing with words is that of precisiated natural language(PNL). PNL is a superset of the language of fuzzy if-then rules. Of particular importance is PNL's role as a concept-definition language.
Computing with words opens the door to a far-reaching enlargement of the role of natural languages in scientific theories and, especially, in information processing, decision and control. The tutorial will cover the basics of both the theory of computing with words and its applications, and will clarify the relationship between computing with words with granular computing and the computational theory of perceptions.
About the Speaker:
Lotfi A. Zadeh is a Professor in the Graduate School, Computer Science Division, Department of EECS, University of California, Berkeley. In addition, he is serving as the Director of BISC (Berkeley Initiative in Soft Computing). He is an alumnus of the University of Teheran, MIT and Columbia University. He held visiting appointments at the Institute for Advanced Study, Princeton, NJ; MIT; IBM Research Laboratory, San Jose, CA; SRI International, Menlo Park, CA; and the Center for the Study of Language and Information, Stanford University. His earlier work was concerned in the main with systems analysis, decision analysis and information systems. His current research is focused on fuzzy logic, computing with words and soft computing, which is a coalition of fuzzy logic, neurocomputing, evolutionary computing, probabilistic computing and parts of machine learning. The guiding principle of soft computing is that, in general, better solutions can be obtained by employing the constituent methodologies of soft computing in combination rather than in stand-alone mode.
Dr. Zadeh is a Fellow of the IEEE, AAAS, ACM and AAAI. He is a member of the National Academy of Engineering and a Foreign Member of the Russian Academy of Natural Sciences. He is a recipient of the IEEE Education Medal, the IEEE Richard W. Hamming Medal, the IEEE Medal of Honor, the ASME Rufus Oldenburger Medal, the B. Bolzano Medal of the Czech Academy of Sciences, the Kampe de Feriet Medal, the AACC Richard E. Bellman Central Heritage Award, the Grigore Moisil Prize, the Honda Prize, the Okawa Prize, the AIM Information Science Award, the IEEE-SMC J. P. Wohl Career Achievement Award, the SOFT Scientific Contribution Memorial Award of the Japan Society for Fuzzy Theory, and other awards and honorary doctorates. He has published extensively on a wide variety of subjects relating to the conception, design and analysis of information/intelligent systems, and is serving on the editorial boards of over fifty journals.
Tutorial WA2
Type 2 Fuzzy Logic Systems
08:30-10:00 July 25, 2001
Part 1: Rule-Based Type-2 Fuzzy Logic Systems
Jerry M. Mendel
Department of Electrical Engineering
University of Southern California
USA
Abstract:
Rule-based fuzzy logic systems are very widely used. They are often subject to the following uncertainties: meanings of words used in the rules (which translates into uncertain membership functions), consequently used in a rule, noisy measurements that activate the FLS, and noisy data used to tune the parameters of the FLS. Paradoxically, a type-1 FLS cannot model and minimize the effects of such uncertainties. A type-2 FLS can. And, if all uncertainties disappear, a type-2 FLS reduces to a type-1 FLS. To-date, applications where either non-stationarity and/or time-variablility (of the data-generating mechanism) are well-suited to type-2 FLSs. In this tutorial all of the elements of a type-2 FLS will be described, some applications of type-2 FLSs will be covered, and access to free software will be explained.
About the Speaker:
Jerry M. Mendel received the Ph.D. degree in electrical engineering from the Polytechnic Institute of Brooklyn, Brooklyn, NY. Currently he is Professor of Electrical Engineering and Associate Director for Education of the Integrated Media Systems Center at the University of Southern California in Los Angeles, where he has been since 1974. He has published over 380 technical papers and is author and/or editor of eight books. His present research interests include: type-2 fuzzy logic applied to digital communication problems, forecasting of time-series, and classification.
Dr. Mendel is a Distinguished Member of the IEEE Control Systems Society. He was President of the IEEE Control Systems Society in 1986. Among his awards are the 1983 Best Transactions Paper Award of the IEEE Geoscience and Remote Sensing Society, the 1992 Signal Processing Society Paper Award, a 1984 IEEE Centennial Medal, and an IEEE Third Millenium Medal.
10:30-12:30 July 25, 2001
Part 2: Type-2 Knowledge Acquisition and Reasoning Systems
I. B. Turksen
Department of Industrial Engineering
University of Toronto
Canada
Abstract:
Type-2 fuzzy rule base systems capture the uncertainties embedded in (I) meanings of words in CWW and perceptions, and (ii) imprecision contained in measurement data during the acquisition and extraction of membership functions. In addition, Type-2 approximate reasoning generates further uncertainties because FDCF, Fuzzy Disjunctive Canonical Forms, and FCCF, Fuzzy Conjunctive Canonical Forms, are separated in contrast to classical reasoning formulas. These two issues will be discussed and their applications will be demonstrated in the tutorial.
About the Speaker:
I.B. Türksen received his Ph.D. degree in Systems Management and Operations Research in 1969, from the University of Pittsburgh, PA. He joined the Faculty of Applied Science and Engineering at the University of Toronto in 1970 and became Full Professor in 1983. Since 1987, he has been Director of the Information/Intelligent Systems Laboratory. During the 1991-1992 academic year, he was Visiting Research Professor of LIFE, Laboratory for International Fuzzy Engineering, Chair of Fuzzy Theory at Tokyo Institute of Technology. During 1993-1994 academic year, he was Visiting Research Professor at the University of South Florida and Bilkent University. Currently he is the President of IFSA. His current research interests are on the foundations of fuzzy sets and logics, in particular on Type 2 fuzzy knowledge representation and reasoning, fuzzy truth tables and fuzzy normal forms, and on applications of intelligent manufacturing and process system models, as well as, management decision support system models for analysis diagnosis, prediction and intelligent control.
Tutorial WA3
Non-linear and Fuzzy Systems Applications in Finance: A Practitioners
View
08:30-12:30 July 25, 2001
Gregg Garrison
Hanseatic Group, Inc.
USA
Abstract:
The Hanseatic Group began business in 1977 as a Commodity Trading Advisor, taking its name from the medieval Hanseatic League. Hanseatic manages a variety of financial programs for institutions and high net worth individuals around the world through its SEC or CFTC-registered affiliates or other alternative investment firms. Hanseatic views markets as dynamically evolving nonlinear systems, a 20th century restatement of the insight at the heart of Adam Smith's invisible hand. Nonlinear systems occur whenever individual parts interact and create a whole that takes on a life of its own that is no longer reducible back to its original component parts. Because of their characteristic nonlinearity, Hanseatic believes markets have more in common with ecology, quantum mechanics, and linguistics, fields in which an array of mathematical tools have been developed to model nonlinear systems. The tools are designed to account for the complex relationships between the parts and the whole as well their interactive change going forward. Hanseatic uses these very same nonlinear tools to model markets quantitatively as well as qualitatively, applying the quantitative approach to its funds management and forecasting businesses and the qualitative approach to manage its private equity investments. These tools have proven very successful in managing various funds (these funds total over $100 million dollars), e.g., Hanseactic's Discretionary (managed futures) fund had a 181.52% return for 2000 and a 1,740.73% accumulated return for the past 5 years.
About the Speaker:
Mr. Garrison attended the University of New Mexico, earning both a MBA in Finance and International Management and a MA in Latin American Studies (Economics and Political Science) in 1997. During his graduate studies, Mr. Garrison began working for Hanseatic Group on strategic marketing, a proposed international joint venture and a comparison of Hanseatic's methodology against other technical systems. He has also worked with Hanseatic and an academic institute to study non-linear systems, neural nets, financial engineering and other alternative approaches in finance and economics. Since June of 1998, Mr. Garrison has been Head of Marketing of Hanseatic's services to individual and institutional clients.
Tutorial WA4
An Introduction to Evolutionary Computation and its Application
to Problems in Fuzzy Systems
08:30-12:30 July 25, 2001
David B. Fogel
Natural Selection, Inc.
USA
Abstract:
This tutorial is meant for people with an interest in real-world applications
of fuzzy systems and other soft computing technologies who
want to learn about the benefits that evolutionary computation can
provide to these efforts. The course will provide an introduction to
the central concepts that underlie evolutionary computation and
detail examples of how to apply these methods to typical problems
addressed with fuzzy systems, including time series prediction,
classification,
clustering, and control. Fundamental issues involving data representation,
search operations, selection, and other facets of problem solving will be
addressed.
About the Speaker:
Dr. David B. Fogel is chief executive officer of Natural Selection, Inc.,
La Jolla, CA. He has been applying computational intelligence methods
to real problems for 16 years. Dr. Fogel is the founding editor-in-chief
of the IEEE Transactions on Evolutionary Computation and is the author
of over 200 publications in computational intelligence, including six books.
Most recently, he published "How to Solve It: Modern Heuristics,"
co-authored by Z. Michalewicz (Springer, 2001). He was elected a Fellow
of the IEEE in 1999. Dr. Fogel is general chairman of the 2002 IEEE
World Congress on Computational Intelligence, to be held May 12-17,
2002 in Honolulu, Hawaii.
|
|
