This document contains the preface.

This document contains the contents.

We all know that computers are suitable in performing mechanical computations, using fixed programmed rules which allow artificial machines to perform simple monotonous tasks efficiently and reliably. Human beings get bored very quickly with monotonous tasks. A computer does not have reasoning and commonsense power like human beings and it is difficult for the computer to understand trouble situations and adapt itself to new situations.

There are a lot of applications of Artificial Intelligence as it is used in a variety of fields for solving complex problems. Applications range from the military for autonomous control and target identification, to the entertainment industry for computer games and robotic pets. Artificial intelligence has been used in a wide range of fields including medical diagnosis, stock trading, robot control, law, remote sensing, scientific discovery and toys.

The state-space search paradigm received early attention from Newell and Simon, who developed a system called GPS (the General Problem Solver) in 1960.
It is an integral component of numerous computer programs is search. So search techniques are heavily studied in the area of computer science. Search is often used in AI, often within the context of state space search. Let’s look at this technique in detail.

Heuristics are approximations used to minimize the searching process. Generally, there are two categories of the problems:
? Problem for which no exact algorithm is known and one needs to find an approximate and satisfying solution, e.g., computer vision, speech recognition etc.
? Problem for which exact solution is known, but computationally infeasible, e.g. chess

Expert system is an application of AI that embodies human expertise. Expert system field become prominent to solve complex problems. Artificial intelligence researchers achieved considerable success over last 50 years in developing expert system technology in order to solve complex real time problems that are difficult to solve using traditional method because of complexity in problem.

Expert system is an application of AI that embodies human expertise. In the recent years expert system has emerged as one of the most powerful tool and approach of Artificial Intelligence field. Expert system is designed for solving complex decision–making problems that simulate human expert capability for taking decision. Rosenman defined expert system as:-
“An automated reasoning system that attempts to mimic the performance of the human expert.”

Before explaining knowledge acquisition it is necessary to understand the meaning of knowledge. Knowledge evolves from data and information. That is refined data is information and refined information is knowledge. Person who possess knowledge are called experts.

In the previous chapter we already discussed about knowledge. Knowledge plays an important role in AI. There is no intelligence without knowledge. For solving complex problems faced in artificial intelligence, large amount of knowledge is required and also require some way of representing and manipulating the knowledge. Knowledge means fact or condition of being aware with something or knowing something gained through experience. So we can say that knowledge may be defined as facts, information or skills that are obtained through several years of experience and education.

The conventional computer ask programmer what they to do and are used for fast arithmetic calculation. Conventional computer are not used for–assisting with noisy data, fault tolerance, huge parallelism, and adapt to conditions. The neural network system is used to formulate algorithmic solution or where we can lots of example of the behavior we require. Neural network follow different examples for computing. The von Neumann machine is based on the processing/ memory abstraction of human information processing. The neural network is based on the parallel architecture of biological neurons. Neural network are an outline of multiprocessor computer system with single processing elements, a high degree of interconnection, communication between elements.

A teacher is present during leaning process. It is a machine learning technique that sets parameters of an artificial neural network from training data. The function of this learning technique is to set the values for any valid input value after having seen output value.

Fuzzy or multivalued logic was introduced in 1930s by Jan Lukasiewicz. He introduced logic that extended range of truth values to all real numbers in the interval between 0 and 1 e.g., possibility that a man 181cm tall is really tall might to be set to a value of 0.86. This can lead to inexact reasoning called possibility theory.

Fuzzy system is also called rule-based system that is constructed from collection of linguistic rules. It is nonlinear mapping from input to output. Fuzzy rule based system is most useful in modeling some complex system that can be observed by humans.

Expert systems are computer programs, that are designed to make use some of the skills of an expert to non experts. Such programs attempt to emulate in some way an expert’s thinking patterns. For Example: Dendral is a first expert system developed in 1965 which determined molecular structure from mass spectrometer data. Mycin is also an expert system used for medical diagnosis. There are no. of approaches for simulating expertise of an expert: Rule based approach, Semantic Net, Frames, Neural Network but out of these important ones are rule based system and neural network.

To represent the problem operation, symbol pattern is used so that intelligent action is attained. When these patterns are used several potential solution are generated, among these solutions a specific search is selected. The language that is used for an AI representation must

In prolog, the mainly two types of input and output predicate. Input and output predicate are the most important predicate in which user read from files and write to files.

This document contains the Index.