Abstract
One of the main aims of artificial intelligence researchers has been to build computer systems that mimic the ability of humans to perceive, reason, and solve "real-life" problems. Traditional AI approaches have been based on the application of formal knowledge representations such as predicate (two-valued) logic symbolic computations. This is a form of "hard" computing which is based on precision, certainty, and rigor. This is also the model of computation that many parallel computing researchers have adopted for solving problems over the last 30 years. It is in sharp contrast to real human reasoning or what is known as "common sense" reasoning. This form of reasoning is based on approximate, rather than precise problem solving techniques. Of these "soft-computing" techniques that have been used to solve a wide range of problems over the last few years, one could mention neural networks, fuzzy logic, cellular automata, and evolutionary techniques.

In this talk, I will overview evolutionary techniques. These are stochastic search and optimization methods that are characterized by their robust performance and are patterned after biological evolution. I will also discuss the potential of using these techniques to solve problems in parallel computing. What makes these techniques very powerful is their simplicity and elegance, and they have been also proven to be robust in solving very complex problems. Many problems in parallel computing lend themselves naturally to this evolutionary paradigm. Furthermore, most evolutionary techniques have a structure that makes them more amenable to parallel computing implementations than many traditional approaches. I will also outline some the open problems that need to be solved in order to more researchers using evolutionary techniques to solve parallel computing related problems.

Biography
Albert Y. Zomaya: is a professor in the department of electrical and electronic engineering at the University of Western Australia, where he also leads the Parallel Computing Research Laboratory. He received his PhD from Sheffield University. The author/co-author of more than 80 publications in technical journals, collaborative books, and conferences, he is an associate editor for the International Journal in Computer Simulation, the Journal of Parallel Algorithms and Applications, and the International Journal on Parallel and Distributed Systems and Networks. He was on the editorial board of the IFAC Control Engineering Journal during the period of 1993-96.

He is also the author of Modelling and Simulation of Robot Manipulators: A Parallel-Processing Approach (World Scientific Publishing, 1992), the co-author (with P.M. Mills and M.O. Tade') of Neuro-adaptive Process Control: A Practical Approach (Wiley, 1996), the editor Parallel Computing: Paradigms And Applications (International Thomson Computer Press, 1996), and the editor-in-Chief of the Parallel and Distributed Computing Handbook (McGraw-Hill, 1996). Dr. Zomaya is a board member of the International Federation of Automatic Control (IFAC) committee on Algorithms and Architectures for Real-Time Control, and a board member of the IEEE Technical Committee on Parallel Processing. He served on the advisory board and program committees of several national and international conferences. He is a chartered engineer and a member of the IEEE, the ACM, the Institute of Electrical Engineers (U.K.), and Sigma Xi. Dr. Zomaya's research interests lie in parallel processing, real-time systems, and computational models for machine learning.