AI TECHNIQUE

 AI TECHNIQUE

      AI problems are of many varieties and they appear to have very little in common. But there are techniques appropriate for the selection of variety of those problems, AI researches have show that “ Intelligence requires knowledge” , and knowledge itself posses some less desirable properties.

It voluminous

It is hard characterize accurately

It is constantly changing

It differs from data

It is organized data

AI techniques EXPLOIT knowledge and for this knowledge must be represented as follows.

AI techniques must be designed keeping in mind the above constraints imposed by AI problems. AI techniques EXPLOIT knowledge and for this knowledge must be represented as follows.

1. Knowledge captures generalizations: Instead of representing individual situations separately , situation that share important properties grouped together . this avoids wastage of ,memory and unnecessary updation.

2. In many AI domains, most of the knowledge a program has, must be provided by people in terms of they understand.

3. It can be easily modified to correct errors.

4. It can be used in several situations even if it is not totally accurate or complete.

5. It can be used to help overcome its own sheer bulk, by helping to narrow the range of possibilities that must be considered.

AI techniques must be designed keeping in mind the above constraints imposed by AI problems.