Skip to main content

Artificial Intelligence

 Artificial intelligence

 Artificial Intelligence means thinking and acting rationally. 


Application Domain : 

  1. Robotics
  2. Memory organization 
  3. knowledge representation
  4. Inference technologies 
  5. Common sense reasons
  6. Dealing with uncertainty and decision making
  7. Understanding Natural Language 
  8. Pattern Recognition 
  9. Speech recognition and synthesis .
  10. and many more ...

Definition of Belief: 

Essentially a meaningful and coherent expression that can be represented - that's a belief may be true or false. 

Hypothesis:

It may be defined as a justified belief that is not known to be true. Thus a hypothesis is a belief that is backed up with some supporting evidence, but it may still be false.

Knowledge:

The justified belief. Knowledge can be defined as the body of fact and principle accumulated by humankind for the state of knowing. The meaning of knowledge is closely related to the meaning of intelligence and a characteristic of intelligence is that it poses some knowledge.
Knowledge can be:-

  1. Declarative: It's passive knowledge expressed as statements of facts. Ex- Personal knowledge in Database.
  2. Procedural: It is compiled knowledge related to some task. Ex- steps to solve an algorithm.
  3. Heuristic: It's a special type of knowledge used by humans to solve a complex problem. It is the knowledge used to make good judgments or strategies, tricks or rule of thumb used to simplify the problem.

Knowledge Base System (KBS)

  • It depends on a rich base of knowledge to perform a difficult task.
  • Real power of an expert system comes from the knowledge it poses rather than the particular inference schemes it employs.

  • KBS gets their power from the expert knowledge that has been coded into facts,rules,heuristic and procedures.
  • The knowledge is stored in a knowledge base separate from control and inference components.


Representation of knowledge:

  • Knowledge consists of facts, rules. It can be represented in different forms-
      1. As spoken or written forms
      2. mental image
      3. As a graphical or pictures.
      4. As a character string, a collection of magnetic spots.
  • The most important technique is FOPL(First-order predicate logic). It has a well-defined theory, the highest reasonable expressive power, and usage valid form of inferring.
  • Other representation schemes include- Frame, associative network (Symantec network ), Fuzzy logic(Generalization of predicate logic), Model logic (Extense of classical logic), object-oriented method. 

Knowledge Organization: 

The organization of knowledge in memory is key to an efficient process. KBS may require thousands of facts and rules to perform its intended task. It is essential that the appropriate facts and rules be easy to locate and retrieve.

Knowledge Manipulation:

  • Decisions and actions in KBS come from the proper manipulation of knowledge in a specified way.
  • The manipulations are the computational equivalent of reasoning - this requires a form of inference or deduction.

Acquisition of Knowledge:

  • One of the greatest bottlenecks in knowledge-rich systems is the acquisition and validation of knowledge. 
  • Knowledge can come from various sources to be useful the knowledge must be accurate and presented at a high level of encoding. It is complete in the sense that all essential rules are maintained free of inconsistencies.
  • The acquisition problem has also stimulated mass research in Machine Learning systems.


Related Topics :     
                                                                                                

 

Labels:

Comments

Post a Comment