introduction to artificial intelligence

            

Introduction to Artificial Intelligence Systems

must design intelligent problem. fold. Some of the number of techno works, fuzzy logic oic, and problem. for more information visit Wikipedia page: introduction to artificial intelligence.

Artificial Intelligence (AD is an area of computer science concerned with designing intelligent computer systems that is, systems that exhibit the characteristics we associate with intelligence in human behavior' (Avron Barr and Feigenbaum, 1981). 'Al is a branch of computer science daria concerned with the automation of intelligent behavior' (Luger and Stubblefield, 1993),

However, the term intelligence is not very well defined and therefore has been less understood. Consequently, tasks associated with intelligence such as learning, intuition creativity, and inference all seem to have been partially understood.

Al in its quest to comprehend, model and implement theories of intelligence, in other words, in its quest to design intelligent systems, has not just registered modest success in developing techniques and methods for intelligent problem solving, but in its relentless pursuit, has fanned out to encompass a number of technologies in its fold. Some of the technologies include but are not limited to expert systems, neural networks, fuzzy logic, cellular automata, and probabilistic reasoning. Of these technologies, neural networks, fuzzy logic, and probabilistic reasoning are predominantly known as soft computing. The term 'soft computing' was introduced by Lotfi A. Zadeh of the University of California, Berkley, U.S.A. Probabilistic reasoning subsumes genetic algorithms, chaos, and parts of learning theory.

According to Zadeh, soft computing differs from hard computing (conventional computing) in its tolerance to imprecision, uncertainty, and partial truth. In effect, the role model is the human mind. Hard computing methods are predominantly based on mathematical approaches and therefore demand a high degree of precision and accuracy in their requirements. But in most engineering problems, the input parameters cannot be determined with a high degree of precision and therefore, the best estimates of the parameters are used for obtaining a solution to problems. This has restricted the use of mathematical approaches for the solution of inverse problems when compared to forward problems.

On the other hand, soft computing techniques, which have drawn their inherent characteristics from biological systems, present effective methods for the solution of even difficult inverse problems. The guiding principle of soft computing is to exploit the tolerance for imprecision, certainty; and partial truth to achieve tractability, robustness, and low-cost solution... Also, ... employment of soft computing for the solution of machine learning problems has led to high MQ (Machine Intelligence Quotient).

Hybrid intelligence systems deal with the synergistic integration of two or more of the technologies. The combined use of technologies has resulted in effective problem-solving in comparison with each technology used individually and exclusively.