------------------------------------------------------------------------------ Speaker: Professor C. S. George Lee School of Electrical and Computer Engineering Purdue University West Lafayette, IN 47907, U.S.A. csglee@purdue.edu Topic: "Structures and Learning of Self-Adaptive Neuro-Fuzzy Systems" Date: Thursday, 13 December 2001 Time: 2:00pm - 3:00pm Venue: Lecture Theater F (Leung Yat Sing Lecture Theater, near lift nos. 25/26) HKUST ABSTRACT Neuro-fuzzy systems are multi-layered connectionist networks that realize the elements and functions of traditional fuzzy logic control/decision systems. The trained neuro-fuzzy systems are isomorphic to a fuzzy logic system, and IF-THEN rule knowledge can be explicitly extracted from the network. This talk presents a brief introduction to self-adaptive neuro-fuzzy systems and addresses our recent research results. Neuro-fuzzy network structures with their associated clustering and learning algorithms will be discussed. Computer simulation examples such as classification of Iris data, prediction of soil liquefaction, and the control of an autonomous underwater robot will be presented to illustrate the performance and applicability of the proposed neuro-fuzzy systems. If time permits, real-time simulation on some applications will be demonstrated. ****************** Biography: Dr. C.S. George Lee is a Professor of Electrical and Computer Engineering at Purdue University, West Lafayette, Indiana, U.S.A. An IEEE Fellow since 1993, Professor Lee's research has been focusing on robotics, assembly, and neuro-fuzzy systems. Professor Lee has authored or co-authored over 140 publications in these areas, in addition to two graduate textbooks, Robotics (McGraw-Hill, 1986) and Neural Fuzzy Systems (Prentice-Hall, 1996), and 20 book chapters. Professor Lee has served as Secretary and Vice-President for Technical Affairs for the IEEE Robotics and Automation Society, Program Chair of 1996 ICRA, and Program Chair of 1998 IROS, and currently serves as an AdCom member. ----------------------------------------------------------------------------