ABSTRACT
For the past three decades, there have been two major groups of researchers in the eld of algorithmic development for real systems; the rst group believes that such development can only be done by using conventional mathematical and probabilistic techniques, whereas the second group emphasizes that there are other methods of applying mathematical knowledge that need not be that restrictive in terms of boundaries and samples. So computing diers from conventional (hard) computing in that, unlike hard computing, it is tolerant of imprecision, uncertainty, partial truth, and approximation. In eect, the role model for so computing is the human mind. Certainly, the way our brain works is dierent from the way a microprocessor works because our brain can get an intuitive “feel” of things rather than exact measured values, and its estimates are perceptive rather than numeric. Hence, the guiding principle of so computing is this: Exploit the tolerance for imprecision, uncertainty, partial truth, and approximation to achieve tractability, robustness, and low solution cost. e basic ideas underlying so computing in its current incarnation have links to many earlier inuences, with Zadeh’s 1965 paper on fuzzy sets holding a pioneering position. In fact, for many years, so computing was being
referred to as fuzzy logic as well. However, the set has grown since, and now the principal constituents of so computing are
Fuzzy systems•
Neural networks•
Precetron-based•
Radial basis functions•
Self-organizing maps•
Evolutionary computation•
Evolutionary algorithms•
Genetic algorithms•
Harmony search•
Swarm intelligence•
Machine learning•
Chaos theory•
What is important to note is that so computing is not an amalgam of various techniques; rather, it is a partnership in which each of the components contributes a distinct methodology to address problems in its domain. is notion has an important consequence: in many cases, a problem can be solved most eectively by using a combination of the constituent techniques rather than exclusively by any single technique. A striking example of a particularly eective combination is what has come to be known as neuro-fuzzy systems. Such systems are becoming increasingly visible as consumer products, ranging from air conditioners and washing machines to photocopiers and camcorders.
