344-571 ????????????? (Artificial Intelligence)

1
344-571 ????????????? (Artificial Intelligence)

• ??.??.?????? ??????????????
• ?????????????????????????? ??????????????
  ????????????????????????
• ????????? CS 108 ???????? 074-288580
• E-mail wwettayaprasit_at_yahoo.com
• Website http//www.cs.psu.ac.th/wiphada

2
????????????

• 1. ???????????????????????????????????????????????
  ?????????????????????????????????
• 2. ???????????????????????????????????????????????
  ?
• 3. ?????????????????????????????????????????????
• ?????????????????? ????????? ?????????
  ?????????????????????????
• ???????? ?????????? 30 ??????????
  40
• LAB Assignment 30
• ???? Artificial Intelligence second edition,
  Elaine Rich and Kevin Knight,
• McGraw-Hill Inc., 1991.

3
???????????
Chapter 1 What is Artificial Intelligence? Chapt
er 2 Problems and Spaces Chapter 3 Heuristic
Search Chapter 4 Natural Language Processing
Chapter 5 Machine Learning Chapter 6
Robotics Chapter 7 Neural Networks
Chapter 8 Expert Systems
Chapter 9 Computer Vision
4
Chapter 1What is Artificial Intelligence?

5
Content

• Artificial IntelligenceArtificial Intelligence
  FieldsHeuristicTic Tac ToeTuring Test

6
Artificial Intelligence

• artificial intelligence
• n. (Abbr. AI)
• The ability of a computer or other machine to
  perform those activities that are normally
  thought to require intelligence.
• The branch of computer science concerned with the
  development of machines having this ability.

7
Artificial Intelligence

• The subfield of computer science concerned with
  understanding the nature of intelligence and
  constructing computer systems capable of
  intelligent action.
• It embodies the dual motives of furthering basic
  scientific understanding and making computers
  more sophisticated in the service of humanity.

8
Artificial Intelligence

• Many activities involve intelligent action
• problem solving, perception, learning,
  planning and other symbolic reasoning,
  creativity, language, and so forthand therein
  lie an immense diversity of phenomena.

9
Artificial Intelligence

• Computer Encyclopedia
• (Artificial Intelligence) Devices and
  applications that exhibit human intelligence and
  behavior including robots, expert systems, voice
  recognition, natural and foreign language
  processing. It also
  implies the ability to learn and adapt through
  experience.

10
Artificial Intelligence

• Wikipedia
• The term Artificial Intelligence (AI) was first
  used by John McCarthy who considers it to mean
  "the science and engineering of making
  intelligent machines".1
• It can also refer to intelligence as exhibited
  by an artificial (man-made, non-natural,
  manufactured) entity.

11
Artificial Intelligence

• Wikipedia
• AI is studied in overlapping fields of computer
  science, psychology, neuroscience and
  engineering, dealing with intelligent behavior,
  learning and adaptation and usually developed
  using customized machines or computers.

12
History of Artificial Intelligence
1950 Alan Turing introduces the Turing test intended to test a machine's capability to participate in human-like conversation.
1951 The first working AI programs were written to run on the Ferranti Mark I machine of the University of Manchester a checkers-playing program written by Christopher Strachey and a chess-playing program written by Dietrich Prinz.
1956 John McCarthy coined the term "artificial intelligence" as the topic of the Dartmouth Conference.
1958 John McCarthy invented the Lisp programming language.
1965 Joseph Weizenbaum built ELIZA, an interactive program that carries on a dialogue in English language on any topic.
1965 Edward Feigenbaum initiated DENDRAL, a 10-yr effort to develop software to deduce the molecular structure of organic compounds using scientific instrument data. It was the first expert system.
13
History of Artificial Intelligence
1966 Machine Intelligence workshop at Edinburgh - the first of an influential annual series organized by Donald Michie and others.
1968 HAL 9000 made its appearance in the science fiction movie 2001 A Space Odyssey.
1972 The Prolog programming language was developed by Alain Colmerauer.
1973 Edinburgh Freddy Assembly Robot a versatile computer-controlled assembly system.
1974 Ted Shortliffe's PhD dissertation on the MYCIN program (Stanford) demonstrated a very practical rule-based approach to medical diagnoses, even in the presence of uncertainty. While it borrowed from DENDRAL, its own contributions strongly influenced the future of expert system development, especially commercial systems.
1997 The Deep Blue chess program (IBM) beats the world chess champion, Garry Kasparov.
1999 Sony introduces the AIBO, an artificially intelligent pet.
2004 DARPA introduces the DARPA Grand Challenge requiring competitors to produce autonomous vehicles for prize money.
14
Artificial Intelligence
Typical problems to which AI methods are applied Typical problems to which AI methods are applied
Pattern recognition Computer vision, Virtual reality and Image processing
Optical character recognition Diagnosis (artificial intelligence)
Handwriting recognition Game theory and Strategic planning
Speech recognition Game artificial intelligence and Computer game bot
Face recognition Natural language processing, Translation and Chatterbots
Artificial Creativity Non-linear control and Robotics
15
AI Areas

• Artificial Intelligence (AI)
• the branch o f computer science that is concerned
  with the automation of intelligent behavior.
• AI Areas
• Game Playing
• Automated Reasoning and Theorem Proving
• Expert Systems
• Natural Language Understanding and Semantics
  Modeling
• Modeling Human Performance
• Planning and Robotics
• Machine Leaning
• Neural Networks

16
Task Domain of AI

• Mundane Tasks mundane(??????) adj. ??????
• Perception Vision, Speech
• Natural language Understanding, Generation,
  Translation
• Commonsense reasoning
• Robot control
• Formal Tasks
• Games Chess
• Mathematics Logic, Geometry
• Expert Tasks
• Engineering Design, Fault finding,
  Manufacturing planning
• Scientific analysis
• Medical diagnosis
• Financial analysis

17
Artificial Intelligence Fields

18
Robotics

• Shakey the Robot Developed in 1969 by the
  Stanford Research Institute, Shakey was the first
  fully mobile robot with artificial intelligence.
  Seven feet tall, Shakey was named after its
  rather unstable movements. (Image courtesy of The
  Computer History Museum, www.computerhistory.org)

19
Robotics

• A legged game from RoboCup 2004 in Lisbon,
  Portugal
• Team ENSCO's entry in the first Grand Challenge,
  DAVID

20
Robotics

• The DARPA Grand Challenge is a race for a 2
  million prize where cars drive themselves across
  several hundred miles of challenging desert
  terrain without any communication with humans,
  using GPS, computers and a sophisticated array of
  sensors. In 2005 the winning vehicles completed
  all 132 miles of the course in just under 7 hours.

21
Robotics

• robot A mechanical device that sometimes
  resembles a human and is capable of performing a
  variety of often complex human tasks on command
  or by being programmed in advance.
• A machine or device that operates automatically
  or by remote control.
• A person who works mechanically without original
  thought, especially one who responds
  automatically to the commands of others.

22
Robotics

• Computer Encyclopedia
• robot
• A stand-alone hybrid computer system that
  performs physical and computational activities.
  Capable of performing many different tasks, it is
  a multiple-motion device with one or more arms
  and joints.
• Robots can be similar in form to a human, but
  industrial robots do not resemble people at all.

23
Robotics

• Huey, Dewey and Louie
• Named after Donald Duck's famous nephews, robots
  at this Wayne, Michigan plant apply sealant to
  prevent possible water leakage into the car. Huey
  (top) seals the drip rails while Dewey (right)
  seals the interior weld seams. Louie is outside
  of the view of this picture. (Image courtesy of
  Ford Motor Company.)

24
Robotics

• Inspect Pipes from the Inside
• Developed by SRI for Osaka Gas in Japan, this
  Magnetically Attached General Purpose Inspection
  Engine (MAGPIE) goes inside gas pipes and looks
  for leaks. This unit served as the prototype for
  multicar models that perform temporary repairs
  while capturing pictures. (Image courtesy of SRI
  International.)

25
Robotics

• Computers Making Computers
• Robots, whose brains are nothing but chips, are
  making chips in this TI fabrication plant. (Image
  courtesy of Texas Instruments, Inc.)

26
Robotics

• How Small Can They Get?
• By 2020, scientists at Rutgers University believe
  that nano-sized robots will be injected into the
  bloodstream and administer a drug directly to an
  infected cell. This robot has a carbon nanotube
  body, a biomolecular motor that propels it and
  peptide limbs to orient itself.

27
Robotics

• ASIMO,
• a humanoid robot manufactured by Honda.

28
Three Laws of Robotics

• A robot may not injure a human being or, through
  inaction, allow a human being to come to harm.
• A robot must obey orders given it by human beings
  except where such orders would conflict with the
  First Law.
• A robot must protect its own existence as long as
  such protection does not conflict with the First
  or Second Law.

29
Computer Vision
30
Computer Vision

• Computer vision
• The technology concerned with computational
  understanding and use of the information present
  in visual images.
• In part, computer vision is analogous (similar)
  to the transformation of visual sensation into
  visual perception in biological vision.

31
Computer Vision

• For this reason the motivation, objectives,
  formulation, and methodology of computer vision
  frequently intersect with knowledge about their
  counterparts in biological vision. However, the
  goal of computer vision is primarily to enable
  engineering systems to model and manipulate the
  environment by using visual sensing.

32
Computer Vision

• Field of robotics in which programs attempt to
  identify objects represented in digitized images
  provided by video cameras, thus enabling robots
  to "see."
• Much work has been done on stereo vision as an
  aid to object identification and location within
  a three-dimensional field of view. Recognition of
  objects in real time.

33
Computer Vision

• Vision based biological species identification
  systems

34
Computer Vision

• Artist's Concept of Rover on Mars,
• an example of an unmanned land-based vehicle.
  Notice the stereo cameras mounted on top of the
  Rover. (credit Maas Digital LLC)

35
Neural Network

• neural network also neural net n.
• A real or virtual device, modeled after the human
  brain, in which several interconnected elements
  process information simultaneously, adapting and
  learning from past patterns

36
Neural Network

• Computer Encyclopedia
• neural network
• A modeling technique based on the observed
  behavior of biological neurons and used to mimic
  (imitate) the performance of a system.

37
Neural Network

• It consists of a set of elements that start out
  connected in a random pattern, and, based upon
  operational feedback, are molded into the pattern
  required to generate the required results.
• It is used in applications such as robotics,
  diagnosing, forecasting, image processing and
  pattern recognition.

38
Neural Network
39
Machine Learning
40
Neural Network

• Accounting Dictionary
• Neural Networks
• Technology in which computers actually try to
  learn from the data base and operator what the
  right answer is to a question.

41
Neural Network

• The system gets positive or negative response to
  output from the operator and stores that data so
  that it will make a better decision the next
  time.
• While still in its infancy, this technology shows
  promise for use in accounting, fraud detection,
  economic forecasting, and risk appraisals.
• The idea behind this software is to convert the
  order-taking computer into a "thinking" problem
  solver.

42
Neural Network

• Britannica Concise Encyclopedia
• neural network
• Type of parallel computation in which computing
  elements are modeled on the network of neurons
  that constitute animal nervous systems.
• This model, intended to simulate the way the
  brain processes information, enables the computer
  to "learn" to a certain degree.

43
Neural Network

• A neural network typically consists of a number
  of interconnected processors, or nodes. Each
  handles a designated sphere of knowledge, and has
  several inputs and one output to the network.
  Based on the inputs it gets, a node can "learn"
  about the relationships between sets of data,
  sometimes using the principles of fuzzy logic.

44
Neural Network

• Neural networks have been used in pattern
  recognition, speech analysis, oil exploration,
  weather prediction, and the modeling of thinking
  and consciousness.

45
Machine Learning

• Sci-Tech Dictionary
• machine learning (m?'shen 'l?rni?)
• (computer science) The process or technique by
  which a device modifies its own behavior as the
  result of its past experience and performance.

46
Machine Learning

• Wikipedia
• machine learning is concerned with the
  development of algorithms and techniques that
  allow computers to "learn".
• At a general level, there are two types of
  learning inductive, and deductive. Inductive
  machine learning methods extract rules and
  patterns out of massive data sets.

47
Machine Learning

• inductive,
• Logic.
• The process of deriving general principles from
  particular facts or instances.
• Mathematics.
• A two-part method of proving a theorem involving
  an integral parameter. First the theorem is
  verified for the smallest admissible value of the
  integer. Then it is proven that if the theorem is
  true for any value of the integer, it is true for
  the next greater value. The final proof contains
  the two parts.

48
Machine Learning

• inductive,
• reasoning from detailed facts to general
  principles
• Rule induction is an area of machine learning in
  which formal rules are extracted from a set of
  observations.

49
Machine Learning

• deductive. Logic.
• The process of reasoning in which a conclusion
  follows necessarily from the stated premises
  inference by reasoning from the general to the
  specific.
• reasoning from the general to the particular
• Deduction is the process of drawing conclusions
  from premises

50
Machine Learning

• Deduction The process of reaching a conclusion
  through reasoning from general premises to a
  specific premise.
• An example of deduction is present in the
  following syllogism
• Premise All mammals are animals.
• Premise All whales are mammals.
• Conclusion Therefore, all whales are animals.

51
Machine Learning

• deduction, in logic, form of inference such that
  the conclusion must be true if the premises are
  true.
• For example,
• if we know that.. all men have two legs
• And that ..John is a man,
• it is then logical to deduce that ..John
  has two legs.

52
Expert System

• expert systemn. Computer Science.
• A program that uses available information,
  heuristics, and inference to suggest solutions to
  problems in a particular discipline.

53
Expert System

• Expert systems
• Methods and techniques for constructing
  human-machine systems with specialized
  problem-solving expertise.
• The pursuit of this area of artificial
  intelligence research has emphasized the
  knowledge that underlies human expertise and has
  simultaneously decreased the apparent
  significance of domain-independent
  problem-solving theory. In fact, new principles,
  tools, and techniques have emerged that form the
  basis of knowledge engineering.

54
Expert System

• Expertise consists of knowledge about a
  particular domain, understanding of domain
  problems, and skill at solving some of these
  problems.
• Knowledge in any specialty is of two types,
  public and private.
• Public knowledge includes the published
  definitions, facts, and theories which are
  contained in textbooks and references in the
  domain of study. But expertise usually requires
  more than just public knowledge.

55
Expert System

• Human experts generally possess private knowledge
  which has not found its way into the published
  literature.
• This private knowledge consists largely of rules
  of thumb or heuristics.
• Heuristics enable the human expert to make
  educated guesses when necessary, to recognize
  promising approaches to problems, and to deal
  effectively with erroneous or incomplete data.

56
Expert System
Category Problem addressed
Interpretations Inferring situation descriptions from sensor data
Prediction Inferring likely consequences of given situations
Diagnosis Inferring system malfunctions from observables
Design Configuring objects under constraints
Planning Designing actions
Monitoring Comparing observations to plan vulnerabilities
Debugging Prescribing remedies for malfunctions
Repair Executing a plan to administer a prescribed remedy
Instruction Diagnosing, debugging, and repairing students' knowledge
57
Natural Language Processing

• Wikipedia
• Natural language processing (NLP) is a subfield
  of artificial intelligence and linguistics. It
  studies the problems of automated generation and
  understanding of natural human languages.
• Natural language generation systems convert
  information from computer databases into
  normal-sounding human language, and natural
  language understanding systems convert samples of
  human language into more formal representations
  that are easier for computer programs to
  manipulate.

58
Natural Language Processing

• We gave the monkeys the bananas because they were
  hungry and We gave the monkeys the bananas
  because they were over-ripe.

• have the same surface grammatical structure.
  However, in one of them the word they refers to
  the monkeys, in the other it refers to the
  bananas
• the sentence cannot be understood properly
  without knowledge of the properties and behaviour
  of monkeys

59
Natural Language Processing
Time flies like an arrow

• A string of words may be interpreted in myriad
  ways. For example,
• time moves quickly just like an arrow does
• measure the speed of flying insects like you
  would measure that of an arrow - i.e. (You
  should) time flies like you would an arrow.
• measure the speed of flying insects like an arrow
  would - i.e. Time flies in the same way that an
  arrow would (time them).
• measure the speed of flying insects that are like
  arrows - i.e. Time those flies that are like
  arrows
• a type of flying insect, "time-flies," enjoy
  arrows (compare Fruit flies like a banana.)

60
Natural Language Processing

• "pretty little girls' school"

• English and several other languages don't specify
  which word an adjective applies to.
• For example, in the string "pretty little girls'
  school".
• Does the school look little?
• Do the girls look little?
• Do the girls look pretty?
• Does the school look pretty?

61
Question Answering 1

• Russia massed troops on the Czech border.

• POLITICS program Corbonell,1980)
• Q1 Why did Russia do this?
• A1...............................................
  .......................
• Q1 What should the United States do?
• A2 ..............................................
  ....................... OR
• A2................................................
  .........................

62
Question Answering 2

• Mary went shopping for a new coat.
• She found a red one she really liked.
• When she got it home, she discovered that it went
  perfectly with her favorite dress.

ELIZA Q1What did Mary go shopping for? A1
............................................. Q2W
hat did Mary find she liked? A2..................
........................... Q3 Did Mary buy
anything ? A3....................................
.........
63
Intelligence require knowledge

1. It is voluminous.
2. It is hard to characterize accurately.
3. It is constantly changing.
4. It differs from data by being organized in a way
   that corresponds to the ways it will be used.

64
Knowledge Representation and Search for AI

• The knowledge captures generalizations.
• It can be understood by people who must provide
  it.
• It can easily be modified to correct errors and
  to reflect changes in the world.
• It can be used in many situations even if it is
  not totally accurate or complete.
• It can use to narrow the range of possibilities
  that must usually be considered.

65
Common Features of AI Problems

1. The use of computer to do the symbolic reasoning.
2. A focus on problems that do not respond to
   algorithmic solutions. ? Heuristic search.
3. Manipulate the significant quantitative features
   of a situation rather than relying on numeric
   methods.
4. Dealing with semantic meaning.
5. Answer that are neither exact nor optimal but
   sufficient.
6. Domain specific knowledge in solving problems.
7. Use meta-level knowledge.

66
Heuristic

• heuristic (hy?-ris'tik) adj.
• Of or relating to a usually speculative
  formulation serving as a guide in the
  investigation or solution of a problem

67
Heuristic

• Of or constituting an educational method in which
  learning takes place through discoveries that
  result from investigations made by the student.
• Computer Science. Relating to or using a
  problem-solving technique in which the most
  appropriate solution of several found by
  alternative methods is selected at successive
  stages of a program for use in the next step of
  the program.

68
Heuristic

• Computer Encyclopedia
• heuristic
• A method of problem solving using exploration and
  trial and error methods. Heuristic program design
  provides a framework for solving the problem in
  contrast with a fixed set of rules (algorithmic)
  that cannot vary.

69
Heuristic

• Business Dictionary
• Heuristic
• Method of solving problems that involves
  intelligent trial and error, such as playing
  chess. By contrast, an algorithmic solution
  method is a clearly specified procedure that is
  guaranteed to give the correct answer.

70
tic tac toe
71
Tic Tac Toe
72
3D Tic Tac Toe
73
Homework 1
Tic-Tac-Toe

• Read program 1, 2 and 3 and discuss the following
  criteria.
• Their Complexity
• Their use of generalization.
• The clarity of their knowledge.
• The extensibility of their approach.

74
Tic-Tac-Toe Program 1
75
Tic-Tac-Toe Program 1
76
Tic-Tac-Toe Program 1

• Board nine element vector representation.
• 0 blank, 1 X, 2
  O
• Moveable Their Complexity 39 19,683
• view vector board as a ternary number (base
  three)

77
Tic-Tac-Toe Program 2
78
Tic-Tac-Toe Program 2
79
Tic-Tac-Toe Program 2
2 blank
3 X
5 O

• Board nine element vector representation.

• an integer indicating which move of the game is
  about to played.
• 1 indicate the first move.
• 9 indicate the last move.
• Board5 2 ? mean blank
• Poswin(p) If it produce (332) 18 ? X can
  win
• p 0 if the player can not win on his next move.
• Poswin(p) If it produce (552) 50 ?O can
  win
• Go(n) Make a move on square n.
• TURN is odd ? if it is playing X
• TURN is even ? if it is playing O
• More efficient in term of space.

80
Tic-Tac-Toe Program 2
81
Tic-Tac-Toe Program 2
82
Tic-Tac-Toe Program 2

• Board nine element vector representation.
• 2 blank, 3 X, 5
  O
• an integer indicating which move of the game is
  about to played.
• 1 indicate the first move.
• 9 indicate the last move.
• Board5 2 ? mean blank
• Poswin(p) If it produce MAGIC SQUARE
• (8 3 4) 15
• p 0 if the player can not win on his next move.
• Go(n) Make a move on square n.
• TURN is odd ? if it is playing X
• TURN is even ? if it is playing O
• More efficient in term of space.

83
Tic-Tac-Toe Program 3
84
Tic-Tac-Toe Program 3
85
Tic-Tac-Toe Program 3

• Board_Position nine element vector representing
  the board, a list of board positions that could
  result from the next move, and a number
  representing as estimate of how likely the board
  position is lead to an ultimate win for the
  player to move.
• Minimax Procedure in chapter 12.
• We maximize the likely hood of winning the game,
  
• While opponent Minimize the likely hood of
  winning the game
• Decide which of a set of board positions is best.
• find highest possible rating.
• consider all the moves the component could make
  next.
• ? See which move is worst for us....
• (Assume the opponent will make that move)
• Look forward many steps in advance.
• Search tree need more time
• Use AI technique

86
The level of the model

1. What is the goal in trying to produce programs
   that do intelligent things that people do?
2. Are we trying to produce programs that do the
   tasks the same way people do?
3. Are we attempting to produce programs that simply
   do the tasks in whatever way appears easiest?

87
Model human performance

• To test psychological theories of human
  performance.
• PAPPY Colby, 1975
• To enable computers to understand human
  reasoning.
• To enable computers to understand computer
  reasoning.

88
TURING TEST
Columbia Encyclopedia
Alan Mathison Turing
89
TURING TEST

• Columbia Encyclopedia
• Turing test, a procedure to test whether a
  computer is capable of humanlike thought. As
  proposed (1950) by the British mathematician Alan
  Turing, a person (the interrogator) sits with a
  teletype machine isolated from two
  correspondentsone is another person, one is a
  computer.

Columbia Encyclopedia
90
TURING TEST

• By asking questions through the teletype and
  studying the responses, the interrogator tries to
  determine which correspondent is human and which
  is the computer.

Columbia Encyclopedia
91
TURING TEST

• The computer is programmed to give deceptive
  answers, e.g., when asked to add two numbers
  together, the computer pauses slightly before
  giving the incorrect sum to imitate what a
  human might do, the computer gives
  an incorrect answer slowly since the interrogator
  would expect the machine to give the correct
  answer quickly.
• If it proves impossible for the interrogator to
  discriminate between the human and the computer,
  the computer is credited with having passed the
  test.

Columbia Encyclopedia
92
Criteria for success

• How will we know if we have succeeded?
• Turing test. Human Computer Person
  asking?
• DENDRAL is a program that analyzes organic
  compounds to determine their structure.
• HUMAN CHEMIST
  COMPUTER

93
Homework 1

• 1. Given the meaning of Artificial Intelligence
  from your point of view. You may add citation
  from searching documents in the web or from the
  text book.
• 2. Given all AI fields with some explanations.

94
Answers.com
95
The End
The road to success is always
under construction
Jim Miller