1 / 39

Knowledge-Based Systems

Knowledge-Based Systems. Artificial Intelligence. Definition: The activity of providing such machines as computers with the ability to display behavior that would be regarded as intelligent if it were observed in humans. History.

oleg-mason
Télécharger la présentation

Knowledge-Based Systems

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Knowledge-Based Systems

  2. Artificial Intelligence • Definition: The activity of providing such machines as computers with the ability to display behavior that would be regarded as intelligent if it were observed in humans.

  3. History • 1956, Dartmouth College. John McCarthy coined term. Same year, Logic Theorist (first AI program. Herbert Simon played a part) • Past 20 or so years, DOD and NSF have funded AI research at top schools (Stanford, Carnegie Mellon, etc.) • Desert Storm opened up new funding (smart bombs, night vision)

  4. Areas of Artificial Intelligence Expert systems AI hardware Robotics Natural language Perceptive systems (vision, hearing) Neural networks Learning Artificial Intelligence

  5. The Appeal of Expert Systems A computer program that attempts to code the knowledge of human experts in the form of heuristics (i.e. a rule of thumb) Two distinctions from DSS 1. has the potential to extend the manager’s problem-solving ability beyond his or her normal capabilities 2. the ability to explain how the solution was reached

  6. Solutions & explanations Instructions & information Knowledge User User interface Know- ledge base Inference engine Problem Domain Development engine An Expert System Model Expert system Expert and knowledge engineer

  7. Expert system model - main parts: • User interface • Knowledge base • Inference engine • Development engine

  8. User Interface • User enters: • Instructions • Information • Expert system provides: • Solutions • Explanations of • Questions • Problem solutions } Menus, commands, natural language, GUI

  9. Knowledge Base • Description of problem domain • Rules: A knowledge representation technique • such as ‘IF:THEN’ logic • networks of rules • Lowest levels provide evidence • Top levels produce 1 or more conclusions • A conclusion is called a Goal variable.

  10. A Rule Set That Produces One Final Conclusion Conclusion Conclusion Conclusion Evidence Evidence Evidence Evidence Evidence Evidence Evidence Evidence

  11. Tiger Giraffe Zebra Ostrich Penguin Albatross Cheetah R9 R10 R11 R12 R13 R14 R15 And And And And And And And And Tawny Dark Long Black Long Can’t Flies Black& Swims spots legs strips neck fly White Well color Ungulate Bird Or Or Mammal R7 R8 R3 R4 Carnivore Or Or And And Feathers And R1 R2 R5 R6 Gives milk Chews Lays Hoofs Hair Flies Eats milk milk eggs cud And A Rule Set That Can Produce More Than One Final Conclusion LEGEND: Rules Action (conclusions) Pointed Forward Claws Conditions teeth Eyes

  12. Rule Selection • Selecting rules to efficiently solve a problem is difficult • Some goals can be reached with only a few rules; rules 3 and 4 identify bird

  13. Inference Engine • Two basic approaches to using rules 1. Forward reasoning (data driven) 2. Reverse reasoning (goal driven)

  14. Forward Reasoning(forward chaining) • Rule is evaluated as: • (1) true, (2) false, (3) unknown • Rule evaluation is an iterative process • When no more rules can fire, the reasoning process stops even if a goal has not been reached

  15. The Forward Reasoning Process Rule 1 T IF A THEN B Rule 7 IF B OR D THEN K Rule 10 Rule 2 F IF K AND L THEN N IF C THEN D T T Rule 3 Rule 8 Rule 12 T T IF N OR O THEN P IF M THEN E IF E THEN L T Rule 4 T IF K THEN F Legend: First pass Rule 9 Rule 5 Rule 11 T T IF (F AND H) OR J THEN M IF G THEN H IF M THEN O Second pass T Rule 6 F Third pass IF I THEN J

  16. Reverse Reasoning(backward chaining) • Divide problem into subproblems • Try to solve one subproblem • Then try another

  17. A Problem and Its Subproblems Rule 10 IF K AND L THEN N Rule 12 Legend: IF N OR O Rule 11 THEN P Problem IF M THEN O Subproblem

  18. A Subproblem Becomes the New Problem Rule 7 IF B OR D THEN K Rule 10 IF K AND LTHEN N Legend: Rule 8 Rule 12 IF E THEN L Problem IF N OR O THEN P Subproblem

  19. T The First Five Problems Are Identified Step 4 Rule 1 Step 3 IF A THEN B Rule 7 Step 2 IF B OR D THEN K Rule 10 Step 1 T Rule 2 IF K AND L THEN N Rule 12 IF C THEN D IF N OR O THEN P Step 5 Rule 3 IF M THEN E IF E THEN L Rule 11 Legend: Problems to be solved IF (F AND H) OR J THEN M IF M THEN O IF M THEN O Rule 9

  20. Rule 12 If N Or O Then P T The Next Four Problems Are Identified Step 8 Rule 4 If K Then F T Step 7 Step 6 Step 9 Rule 5 If G Then H If M Then O IF (F And H) Or J Then M T T T Rule 9 Rule 11 Legend: Problems to be solved Rule 6 If I Then J

  21. Forward Versus Reverse Reasoning • Reverse reasoning is faster than forward reasoning • Reverse reasoning works best when • there are multiple goal variables • there are many rules • all or most rules do not have to be examined in the process of reaching a solution

  22. Handling Uncertainty • Two types of uncertainty • Rules • Conditions • Certainty factors (CFs) range from 0.00 to 1.00

  23. Development Engine • Programming languages Lisp, Prolog, and recently C++ • Expert system shells

  24. Role of the Systems Analyst • Knowledge engineers work with the expert in designing expert systems • Beyond traditional analyst skills, the following skills are needed • understand how the expert applies his or her knowledge • be able to extract the description of the knowledge (rules as well as facts)

  25. System Development Process • Initiate the development process • Develop the expert system prototype • User participation • Expert system maintenance

  26. Prototyping Approach • A new player: the expert • Delayed user involvement • Need for maintenance

  27. Prototyping Is Incorporated in the Development of an Expert System Systems analyst Expert User Study the problem domain step 1 Study the Problem domain step 2 Define the problem step 3 Specify the rule set Need to redesign Need to redesign step 4 Test the prototype system step 5 Construct the interface step 6 Conduct user tests step 7 Use the system step 8 Maintain the system

  28. Example:Financial Expert System • Credit approval • Knowledge base for the example consists of rules and a mathematical model • User interface • Five decision categories; credit amount influences weightings

  29. Weightings of the Information Categories $5,000 to $20,000 to Category $20,000 $50,000 Financial strength 0.65 0.70 Payment record 0.18 0.20 Customer background 0.10 0.05 Geographical location 0.05 0.03 Business potential 0.02 0.02 Total 1.00 1.00

  30. Expert System Advantages • To managers • Consider more alternatives • Apply high level of logic • Have more time to evaluate decision rules • Consistent logic • To the firm • Better performance from management team • Retain firm’s knowledge resource

  31. Expert System Disadvantages • Can’t handle inconsistent knowledge • Can’t apply judgment or intuition

  32. Neural Networks • Expert systems should be able to learn, and improve their performance • Neural net design -- a bottom-up approach to modeling human intuition

  33. The Human Brain • Neuron -- the information processor • Input -- dendrites • Processing -- soma • Output -- axon • Neurons are connected by the synapse

  34. Simple Biological Neurons Soma (processor) Axonal Paths (output) Synapse Axon Dendrites (input)

  35. Artificial Neural Systems (ANS) • McCulloch-Pitts mathematical neuron function (late 1930s) • Hebb’s learning law (early 1940s) • Neurocomputers • Marvin Minsky’s Snark (early 1950s) • Rosenblatt’s Perceptron (mid 1950s)

  36. Current Methodology • Mathematical models • Complex networks • Repetitious training -- the ANS “learns” by example. An ANS can learn; an expert system cannot.

  37. y1 w1 w2 y2 w3 y3 y wn-1 yn-1 Single Artificial Neuron

  38. OUT1 OUTn The Multi-Layer Perceptron Input Layer Y1 Yn2 OutputLayer IN1 INn

  39. Prerequisite Activities for the EIS Information needs Information technology standards Analysis of organization Corporate data model Information systems plan Production and performance systems EIS

More Related