Chapter 11: Artificial Intelligence

Transcription

1 Chapter 11: Artificial Intelligence Computer Science: An Overview Tenth Edition by J. Glenn Brookshear Presentation files modified by Farn Wang Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley

2 Chapter 11: Artificial Intelligence 11.1 Intelligence and Machines 11.2 Perception 11.3 Reasoning 11.4 Additional Areas of Research 11.5 Artificial Neural Networks 11.6 Robotics 11.7 Considering the Consequences Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-2

3 Intelligent Agents Agent: A device that responds to stimuli from its environment Sensors Actuators Much of the research in artificial intelligence can be viewed in the context of building agents that behave intelligently Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-3

4 Artificial intelligence - coining the buzzword John McCarthy, Dartmouth College summer, 1956 suggested a study of artificial intelligence be carried out to explore the conjecture that every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it. Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-4

5 Levels of Intelligent Behavior Reflex: actions are predetermined responses to the input data Is kick on knocking intelligent? Is swimming intelligent? Is bike riding intelligent? More intelligent behavior requires knowledge of the environment and involves such activities as: Goal seeking Learning Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-5

6 Intelligence in reflexion Look at the center wheel. Tell me what the other wheels are doing? Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-6

7 Intelligence in reflexion Which cycles are rotating? Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-7

8 Intelligence in reflexion Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-8

9 Intelligence in reflexion What is the color of the empty dot? Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-9

10 Intelligence in reflexion Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-10

11 Intelligence in reflexion Which rectangle is taller? Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-11

12 Intelligence in reflexion Which rectangle is taller? Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-12

13 What is intelligence? It is needed in solving difficult problems with no guaranteed solutions. It cannot be prescribed as a fixed set of rules. It relies on common senses. It must be adaptive with learning capabilities. It works most of the time, but may fail occasionally. Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-13

14 The eight-puzzle - a game needs multitudes of intelligence Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-14

15 Our puzzle-solving machine Taking photos of the puzzle. Recognize the configuration of the puzzle. Compute the next move. Move the tiles. Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-15

16 Approaches to Research in Artificial Intelligence Engineering track Performance oriented Theoretical track Simulation oriented Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-16

17 Turing Test Test setup: Human interrogator communicates with test subject by typewriter. Test: Can the human interrogator distinguish whether the test subject is human or machine? Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-17

18 Techniques for Understanding Images Template matching Two steps approach: Image processing edge enhancement region finding smoothing Image analysis motion detection face recognization Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-18

19 Techniques for Understanding Images for the puzzle Template matching 3-D pattern matching is difficult. restrictive and difficult to scale! Two steps approach: Image processing Image analysis to recognize a tile with different focal lengths and angles. to recognize a number with various fonts and hand writings. Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-19

20 Language Processing Syntactic Analysis Semantic Analysis knowledge representation knowledge retrieval Contextual Analysis interpretation of sentences according to contexts common senses Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-20

21 Language Processing Syntactic Analysis Cinderella had a ball. subject verb object. Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-21

22 Language Processing Syntactic Analysis subject? object? Stampeding cattle can be dangerous. subject? verb Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-22

23 Language Processing Semantic Analysis Mary gave John a birthday card. John got a birthday card from Mary. knowledge representation how to represent the true meaning? information retrieval key words? information extraction frames, templates? Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-23

24 A semantic net Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-24

25 Language Processing Contextual Analysis interpretation of sentences according to contexts Cinderella had a ball. Do you know what time it is? common senses Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-25

26 Production Systems (Expert systems) Components 1. Collection of states Start (or initial) state Goal state (or states) 2. Collection of productions: rules or moves Each production may have preconditions 3. Control system: decides which production to apply next Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-26

27 Production Systems (Expert systems) Components 1. Collection of states 2. Collection of productions: rules or moves 3. Control system: decides which production to apply next genetic programming, neural networks, ant intelligence, fuzzy logics, non-monotonic logics Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-27

28 Reasoning by Searching State Graph: All states and productions Search Tree: A record of state transitions explored while searching for a goal state Breadth-first search Depth-first search Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-28

29 A small portion of the eight-puzzle s state graph in backward reasoning for breadth-first search Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-29

30 A small portion of the eight-puzzle s state graph in backward reasoning for depth-first search Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-30

31 Deductive reasoning in the context of a production system Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-31

32 An unsolved eight-puzzle Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-32

33 A sample search tree - breadth-first search Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-33

34 A sample search tree - depth-first search Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-34

35 Productions stacked for later execution - as a log Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-35

36 Heuristic Strategies Heuristic: A rule of thumb for making decisions Requirements for good heuristics Must be easier to compute than a complete solution Must provide a reasonable estimate of proximity to a goal Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-36

37 An unsolved eight-puzzle Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-37

38 An algorithm for a control system using heuristics Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-38

39 The beginnings of our heuristic search Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-39

40 Figure The search tree after two passes Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-40

41 The search tree after three passes Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-41

42 The complete search tree formed by our heuristic system Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-42

43 Handling Real-World Knowledge Representation and storage Accessing relevant information Meta-Reasoning Closed-World Assumption Frame problem from animation how to move a table with the knowledge that the glass on the table could fall and break. Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-43

44 Learning Imitation Supervised Training Reinforcement Evolutionary Techniques Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-44

45 Artificial Neural Networks Artificial Neuron Each input is multiplied by a weighting factor. Output is 1 if sum of weighted inputs exceeds the threshold value; 0 otherwise. Network is programmed by adjusting weights using feedback from examples. Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-45

46 Neural networks Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-46

47 A neuron in a living biological system Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-47

48 Neural networks Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-48

49 Neural network configurations Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-49

50 The activities within a processing unit Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-50

51 Representation of a processing unit Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-51

52 A neural network with two different programs Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-52

53 An artificial neural network Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-53

54 Training an artificial neural network Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-54

55 Training an artificial neural network (continued) Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-55

56 Training an artificial neural network (continued) Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-56

57 Training an artificial neural network (continued) Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-57

58 The structure of ALVINN - Autonomous Land Vehicle in a Neural Net Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-58

59 Associative Memory Associative memory: The retrieval of information relevant to the information at hand One direction of research seeks to build associative memory using neural networks that when given a partial pattern, transition themselves to a completed pattern. Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-59

60 An artificial neural network implementing an associative memory Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-60

61 The steps leading to a stable configuration Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-61

62 Robotics Truly autonomous robots require progress in perception and reasoning. Major advances being made in mobility Plan development versus reactive responses Evolutionary robotics Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-62

63 Issues Raised by Artificial Intelligence When should a computer s decision be trusted over a human s? If a computer can do a job better than a human, when should a human do the job anyway? What would be the social impact if computer intelligence surpasses that of many humans? Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-63