VLSI Design & Test Seminar, Spring 2008 (ELEC7950) Methods of Computational Intelligence Speaker: Bogdan M. Wilamowski, wilambm@auburn.edu Date: Wednesday, February 20, 2008 Time: 4:00 pm Room: Broun 235 ABSTRACT: Comparison of various methods of computational intelligence is presented and illustrated with examples. These methods include neural networks, fuzzy systems, and evolutionary computation. The presentation is focused on neural networks, fuzzy systems and neuro-fuzzy architectures. Various leaning methods of neural networks including supervised and unsupervised methods are presented and illustrated with examples. General learning rule as a function of the incoming signals is discussed. Other learning rules such as Hebbian learning, perceptron learning, LMS - Least Mean Square learning, delta learning, WTA – Winner Take All learning, and PCA - Principal Component Analysis are presented as derivations of the general learning rule. Architecture specific learning algorithms for cascade correlation networks, Sarajedini and Hecht-Nielsen networks, functional link networks, polynomial networks, counterpropagation networks, RBF-Radial Basis Function networks are described. Dedicated learning algorithms for on chip neural network training are also evaluated. The presentation focuses on various practical methods such as Quickprop, RPROP, Back Percolation, Delta-bar-Delta and others. Main reasons of convergence difficulties such as local minima or flat spot problems are analyzed. More advance gradient-based methods including pseudo inversion learning, conjugate gradient, Newton and LM Levenberg-Marquardt, NBN learning algorithms will be also presented. Dr. Bogdan (Dan) M. Wilamowski is Director of AMSTC – Alabama Microelectronics Science and Technology Center and Professor of Electrical and Computer Engineering Department at Auburn University. He was the Director of the Institute of Electronics (1979-1981) and the Chair of the Solid State Electronics Department (1987-1989) at the Technical University of Gdansk, Poland. He was VP for Research at Research Center for Specialized Integrated Circuits, Torun, Poland. (1987-1989). He was Professor at the University of Wyoming (1989-2000). From 2000 to 2003, he was Associate Director of Microelectronics Research and Telecommunication Institute at University of Idaho and he was a Professor in Electrical and Computer Engineering Department and in Computer Science Department at the University of Idaho. Dr. Wilamowski was with the Communication Institute at Tohoku University, Japan (19681970) and he spent one year at the Semiconductor Research Institute, Sendai, Japan as a JSPS Fellow (1975-1976). He was a visiting scholar at Auburn University (1981-1982 and 1995-1996), and a visiting professor at the University of Arizona, Tucson (1982-1984). Dr. Wilamowski received two PhDs one in Computer Science and another in Electrical Engineering. He is the author of four textbooks, about 90 journal and 190 conference publications, and 27 patents. His main areas of interest are: computational intelligence including neural networks and fuzzy systems, electron devices and solid-state electronics, mixed signal and analog signal processing, CAD development, computational intelligence, and network programming. He was the major professor for about 120 graduate students. For contributions to industrial electronics and static induction devices he was named IEEE Fellow in 2000. Dr. Wilamowski was instrumental in establishing the IEEE Jun-ichi Nishizawa Medal and currently serves as the Chair of the Medal Selection Committee. In Industrial Electronics Society he has served as Newsletter Editor (1997-1999), Member of Finance Committee (1997-2004), Treasurer (1998-2001), President Elect (2001-2003), President (2004-2005); in Neural Network Society/Council he served as AdCom Member (1998-2004), VP for Finance and Treasurer (2001-2003). Currently he is VP for Finance the IEEE Computational Intelligence Society He is currently Associate Editor for: IEEE Transactions on Industrial Electronics, IEEE Transactions on Industrial Informatics, IEEE Transactions on Neural Networks, IEEE Transactions on Education, International Journal of Hybrid Intelligent Systems, Journal of Intelligent and Fuzzy, and Journal of Computing. He served as the General Chair, Technical Program Committee Chair, and Member of Organization Committees of various conferences such as IECON, ISIE, ICIPS, ICRAM, IIZUKA, ITM, and ICIT. Contact: Vishwani Agrawal, vagrawal@eng.auburn.edu