Ans. Knowledge consists of facts, concepts, rules, and so forth. It can be represented in different forms, as mental images, as spoken or written words in some language, as graphical or other pictures, and as character strings or collection of magnetic spots stored in a computer as shown in the following figure.

The above figure shows the different levels of knowledge representation. Knowledge acquisition & validation is the greatest bottleneck in building knowledge rich systems. Knowledge can come from various sources, such as experts, textbooks, reports, technical articles, and the like. To be useful, the knowledge must be accurate, presented at the right level for encoding, complete in the sense that all essential facts and rules are included, free of inconsistencies. The acquisition problem has stimulated research in machine learning systems (the systems that can learn new knowledge autonomously without the aid of humans). Since knowledge based systems depend on large quantities of high quality knowledge for their success, it is essential that better methods of acquisition, refinement, and validation be developed.