Logo 
Search:

Artificial Intelligence Articles

Submit Article
Home » Articles » Artificial Intelligence » MaterialRSS Feeds

Artificial Intelligence and Expert Systems, Problems of AI domain and AI techniques

Posted By: Shruti Sharma     Category: Artificial Intelligence     Views: 10601

This article explains about Artificial Intelligence and Expert Systems. Problems of AI domain and AI techniques.

What is Artificial Intelligence And Expert System?

  • AI is a study of how to make computers do things at which, at the moment People are better
  • To Attempt any problem that is complex enough for the computer, we require to learn new methods to solve problems then to use conventional methods.
  • AI and ES teaches us the same

Problems of AI Domain

1. Mundane Tasks
2. Formal Tasks
3. Expert Tasks


Mundane Tasks
- Perception
     -Vision
     - Speech
- Natural Language
     -Understanding
     - Generation
     - Translation
- Commonsense reasoning
- Robot Control

Formal Tasks
Games
      - Chess, Backgammon, Checkers, Go
Mathematics
      - Geometry, Logic, Integral      Calculus, Proving properties of programs

Expert Tasks
Engineering
    Design, Fault Finding, Manufacturing Planning
Scientific Analysis
Medical Diagnosis
Financial Analysis

The Underlying Assumption
  • The Physical Symbol System Hypothesis
  • Symbols as part of expressions
  • System containing symbol structures
  • Expressions producing other expressions
  • A physical symbol system produces, through time, an evolving collection of SS
  • PSS has necessary and sufficient means for general intelligent action
  • Only empirical way to prove (or Disprove!)

Using Computer For It
  • Lady Lovelace and ‘Using computers for other things then number crunching’
  • Computers to test the PSS hypothesis
  • Sophistication in programming to solve more complex problems
  • Sub-symbolic systems like visual perception provide evidences in favor
  • Psychologists to test the theory of intelligence and building programs that behave live humans

The AI Technique

Intelligence requires knowledge
  • Voluminous
  • Hard to characterize accurately
  • Constantly changing
  • To be organized in a way to be used
AI Methods should exploit knowledge
  • Generalization
  • Input comes as ‘human understandable form’
  • Modifiable with meta-knowledge
  • Usable even when incomplete or  not totally accurate
  
Share: 

 
 


Shruti Sharma
Shruti Sharma author of Artificial Intelligence and Expert Systems, Problems of AI domain and AI techniques is from United States. Shruti Sharma says Hello Everyone,
I am Shruti Sharma from United States
 
View All Articles

 
Please enter your Comment

  • Comment should be atleast 30 Characters.
  • Please put code inside [Code] your code [/Code].

 
No Comment Found, Be the First to post comment!