Artificial intelligence (AI) : Part Four

Artificial intelligence (AI) is the branch of computer sciences and known to be the intelligence of machines or the design and study of intelligent agents. Johan Mc Carthy is one who made the term in 1956. Artificial intelligence has now become the most essential part of the technology industry which is providing the best solutions for the most difficult problems in computer science.

AI research is counted among the highly technical and specialized which is divided into subfields. The innermost dilemma of AI comprise such character as logic, information, development, knowledge, communication, observation and the ability to move and control objects.

Branches of AI

Search-Its use is when looking for large no of possibilities, e.g. moves in a chess game or theorem proving program. Discoveries are repeatedly made about how to do this more professionally in a variety of domains.

Pattern Recognition-Whenever program makes comments of some kind, it is often planned to compare what it sees with a sample. For example, a visualization program may try to match a pattern of eyes and a nose in a picture in order to find a face.

Representation-When facts about the world have to be symbolized in some way then usually languages of mathematical logic are used.

Inference-From some facts, others can be gathered. The easiest kind of non-monotonic reasoning is default reasoning in which a termination is to be deduced by default, but the conclusion can be withdrawn if the proof is different.

Common Sense Knowledge and Reasoning-This is the area in which AI is utmost from human- point, in spite of the reality that it has been an active study area since the 1950s. While there has been important growth, e.g. in growing systems of non-monotonic analysis and hypothesis of action, yet more new thoughts are desired.

Learning from Experience- There is also learning of laws expressed in logic. Programs can only learn what facts or behaviors their formalisms can correspond to, and unluckily learning systems are almost all based on very restricted skills to represent information.

Planning-Planning programs are the facts about the effects of actions, particular situation and a statement of a goal and they produce a policy for achieving the goal. In the most common situations, the approach is just a chain of measures.

Epistemology-The study about the knowledge which solves problems in the world.

Ontology- Study of the things that exist, starts in 1990. The programs and verdict deal with diverse kinds of objects, and we study what these diversities are and their basic properties.

Heuristics- A way of trying to learn something or an idea imbedded in a program. The term is used diversely in AI. In some approaches Heuristic functions are used to measure how far a node in a search tree seems to be from a goal.

Genetic Programming-Technique for getting programs to resolve a job by mating random Lisp programs and selecting fittest in millions of generations.

logical AI- What a program knows about the world in general the facts of the exact condition in which it must perform, and its goals are all characterized by sentences of some mathematical logical language. The program chooses what to do by gathering that definite events are suitable for attaining its goals. The example of this branch is Enterprise Resource Planning(ERP).