1. Artificial Intelligence Introduction Chapter 1, AIMA

2. What you’ll learn from this course What is meant by AI –What tools are used –What problems are approached How problems can be solved (exactly and approximately) with search –Game playing How knowledge can be represented –Symbolic (e.g. logic) –Non-symbolic (e.g. neural networks) How logical reasoning (under certainty and under uncertainty) can be done with a machine. How a machine can learn (machine learning) An overview course

3. Course structure 20 hrs. of lectures [T Rögnvaldsson] Exercises (programming) [P-Å Jovall] Homework (with feedback) [T Rögnvaldsson] Examination project (tournament) –Play poker against each other [P-Å Jovall] Oral exam [T Rögnvaldsson] You are expected to be active with homework (programming and analysis) The content follows the AIMA book closely

4. Course web page http://www2.hh.se/staff/denni/courses/AI/aiCourse07.html Will be linked from my home page http://islab.hh.se/islab/islab/people/rognvaldsson.html

6. What is done in AI? Game Playing (Deep Blue Chess program, TD-gammon, …) Handwriting recognition (Apple, IBM, Microsoft,...) Speech Recognition (PEGASUS spoken language interface to American Airlines’ EAASY SABRE reservation system, Apple interface, …) Human-computer interaction (COG, KISMET) Navigation & problem solving (NASA Rover, MARS Beagle) Computer Vision (Face recognition, ALVINN,…) Expert Systems Diagnostic Systems (Microsoft Office Assistant in Office 97) Planning/scheduling (DARPA DART, ARPI) Web search tools (Google,...) Games and movies (eg. Lord of the Rings, Age of Empires,...)

7. The ”pong” video arcade game 00 First public in 1972. The computer moves by calculating where the ball will cross the goal line and move the paddle there. Depending on difficulty, it sometimes does not move fast enough or moves to the wrong spot with some probability.

10. Games: Chess & IBM deep blue Deep Blue relies on computational power, search and evaluation. Deep Blue evaluates 20010 6 positions per second. (Garry Kasparov evaluates 3 positions per second) The Deep Blue is a 32-node IBM RS/6000 SP with P2SC processors. Each node of the SP employs a single micro-channel card containing 8 dedicated VLSI chess processors, for a total of 256 processors working in tandem. Deep Blue calculates 100-200 billion (10 9 ) moves in three minutes. Deep blue typically searches 6 moves ahed but can go as far as 10-20 moves. Deep Blue beat the world champion Garry Kasparov in 1997 ”quantity has become quality”. Deep Blue is “brute force”. Humans (probably) play chess differently... http://www.research.ibm.com/deepblue/meet/html/d.3.html

11. Games: Chess & IBM deep blue Deep Blue relies on computational power, search and evaluation. Deep Blue evaluates 20010 6 positions per second. (Garry Kasparov evaluates 3 positions per second) The Deep Blue is a 32-node IBM RS/6000 SP with P2SC processors. Each node of the SP employs a single micro-channel card containing 8 dedicated VLSI chess processors, for a total of 256 processors working in tandem. Deep Blue calculates 100-200 billion (10 9 ) moves in three minutes. Deep blue typically searches 6 moves ahed but can go as far as 10-20 moves. Deep Blue beat the world champion Garry Kasparov in 1997 ”quantity has become quality”. Deep Blue is “brute force”. Humans (probably) play chess differently... http://www.research.ibm.com/deepblue/meet/html/d.3.html Note: in 1957, AI researchers thought that computers would beat the world chess champion within 10 years.

12. Do humans play chess differently? Compare with HAL (the computer in ”2001: A Space Odyssey”). HAL plays ”tricky” and exploits the lower level of the opponent (the Astronaut Poole). This is not ”computer-like”, but ”human-like”. Computers, on the other hand, assume that the opponent will make the best possible move. Check out ”How HAL plays chess: http://mitpress.mit.edu/e-books/Hal/chap5/five1.html

13. An early chess machine Wolfgang von Kempelen “The Turk”: A doll in Turkish costume seated at a desk with a chessboard. (constructed in 1769) It was first demonstrated that no one was concealed inside, then the mechanism was wound up and the machine set in operation (rewinding every 12 moves). It almost always won the chess game. See http://web.onetel.net.uk/~johnrampling/turk.html

14. An early chess machine E. A. Poe: ” The Automaton does not invariably win the game. Were the machine a pure machine this would not be the case – it would always win” (This is speculation) Wolfgang von Kempelen “The Turk”: A doll in Turkish costume seated at a desk with a chessboard. (constructed in 1769) It was first demonstrated that no one was concealed inside, then the mechanism was wound up and the machine set in operation (rewinding every 12 moves). It almost always won the chess game.

15. TD-Gammon The best backgammon programs use temporal difference (TD) algorithms to train a back-propagation neural network by self-play. The top programs are world-class in playing strength. 1998, the American Association of Artificial Intelligence meeting: NeuroGammon won 99 of 100 games against a human grand master (the current World Champion). TD-Gammon is based more on pattern recognition than search. TD-Gammon is an example of machine learning. It plays itself and adapts its “rules” after each game depending on wins/losses. http://satirist.org/learn-game/systems/gammon/

16. Black & White

17. AI in creatures Symbolic attribute-value pairs Decision trees Neural Networks

18. Handwriting recognition: Apple Newton First handwritten character recognition poor. Artificial Neural Networks give better performance. In production 1995. “...vastly improved hand- writing recognition...” (BYTE May 1996) The Mac OS has native support for pen input, known as Inkwell. Based on Newton.

19. Handwriting rec.: MS TabletPC Current version uses Artificial Neural Networks for recognizing characters.

20. HCI: COG & Kismet COG Kismet What is Kismet (soft) ? What is Kismet (hard) ? Kismet & Rich

21. Navigating: Mars Autonomy Project http://www.frc.ri.cmu.edu/projects/mars/dstar.html Project at Carnegie Mellon, Pittsburgh Project at JPL, Pasadena

22. Navigating: Under water McGill Aqua project

23. Autonomous driving on earth Stanley: The first car to finish ”the grand challenge”. Autonomous driving 350 km in the desert. It took 6 hrs and 54 min, with an average speed of about 50 km/h Stanford-group, lead by Prof. Sebastian Thrun.

24. Next: Urban Challenge November 3:rd 2007 Autonomous driving 100 km in city environment in max 6 hours (about 15 km/h on average). Follow all traffic rules Other vehicles

25. Navigating: Vacuum cleaners How do you guarantee that the vacuum cleaner doesn’t get stuck and that it cleans the entire floor? Small programs ~ 256 B

26. Navigating: helping elderly

27. Navigating: Waiters??

28. Navigating: Web search Google...and more

29. DARPA Military planning http://www.rl.af.mil/div/IFT/IFTB/arpi/arpi.html “DARPA reported that an AI-based logistics planning tool, DART, pressed into service for operations Desert Shield and Desert Storm, completely repaid its three decades of investment in AI research.“ D.L. Waltz, NEC Institute

30. Scientific American January 2007

31. Robots at home World Robotics Report 2004 & 2006 Robots in the homes Lawn mowers & vacuum cl. Toys

32. Computers...

33. ...become cheaper and cheaper Computer memory becomes cheaper at a similar rate; half as expensive in two years. A ”MIPS” becomes 1,000,000 cheaper in 40 years. About half the price in one year. (1 MIPS = 1 million ”instructions” per second) Image from Moravec

34. What is AI? “A field that focuses on developing techniques to enable computer systems to perform activities that are considered intelligent (in humans and other animals).” [Dyer] “The science and engineering of making intelligent machines, especially intelligent computer programs. It is related to the similar task of using computers to understand human intelligence, but AI does not have to confine itself to methods that are biologically observable.” [McCarthy] “The design and study of computer programs that behave intelligently.” [Dean, Allen, & Aloimonos] “AI, broadly defined, is concerned with intelligent behavior in artifacts. Intelligent behavior, in turn, involves perception, reasoning, learning, communicating, and acting in complex environments.” [Nilsson] “The study of [rational] agents that exist in an environment and perceive and act.” [Russell & Norvig]

35. What is AI? “[The automation of] activities that we associate with human thinking…” Bellman, 1978 “The study of mental faculties through the use of computational models” Charniak & McDermott, 1985 “The art of creating machines that perform functions that require intelligence when performed by people.” Kurzweil, 1990 “The branch of computer science that is concerned with the automation of intelligent behavior.” Luger, 2002

36. What is AI? “[The automation of] activities that we associate with human thinking…” Bellman, 1978 Thinking like a human “The study of mental faculties through the use of computational models” Charniak & McDermott, 1985 “The art of creating machines that perform functions that require intelligence when performed by people.” Kurzweil, 1990 “The branch of computer science that is concerned with the automation of intelligent behavior.” Luger, 2002

37. What is AI? “[The automation of] activities that we associate with human thinking…” Bellman, 1978 Thinking like a human “The study of mental faculties through the use of computational models” Charniak & McDermott, 1985 Thinking rationally “The art of creating machines that perform functions that require intelligence when performed by people.” Kurzweil, 1990 “The branch of computer science that is concerned with the automation of intelligent behavior.” Luger, 2002

38. What is AI? “[The automation of] activities that we associate with human thinking…” Bellman, 1978 Thinking like a human “The study of mental faculties through the use of computational models” Charniak & McDermott, 1985 Thinking rationally “The art of creating machines that perform functions that require intelligence when performed by people.” Kurzweil, 1990 Acting like a human “The branch of computer science that is concerned with the automation of intelligent behavior.” Luger, 2002

39. What is AI? “[The automation of] activities that we associate with human thinking…” Bellman, 1978 Thinking like a human “The study of mental faculties through the use of computational models” Charniak & McDermott, 1985 Thinking rationally “The art of creating machines that perform functions that require intelligence when performed by people.” Kurzweil, 1990 Acting like a human “The branch of computer science that is concerned with the automation of intelligent behavior.” Luger, 2002 Acting rationally

40. What is AI? “[The automation of] activities that we associate with human thinking…” Bellman, 1978 Thinking like a human “The study of mental faculties through the use of computational models” Charniak & McDermott, 1985 Thinking rationally “The art of creating machines that perform functions that require intelligence when performed by people.” Kurzweil, 1990 Acting like a human “The branch of computer science that is concerned with the automation of intelligent behavior.” Luger, 2002 Acting rationally

41. The Turing test – acting like a human Suggested by Alan Turing in 1950. If the interrigator cannot distinguish the human from the machine (robot), solely on the basis of their answers to questions, then the machine can be assumed intelligent. © B.J. Copeland 2000

42. The Turing test provides... An objective notion of intelligence –No discussion on the ”true” nature of intelligence. A way to avoid confusion by looking at how the computer reasons, or if it is conscious. A way to avoid bias in favour of the human, by just focusing on the written answers. The Turing test can of course be generalized to other fields besides conversation. But it focuses too much on human behavior. We are not trying to build humans (we already know how to do this...)

43. Problems with Turing test A test of the judge as well of the AI machine Promotes imitators (con-artists). See www.loebner.netwww.loebner.net Chat bots: http://www.abenteuermedien.de/jabberwock/index.php http://www.alicebot.org/ http://www.abenteuermedien.de/jabberwock/index.php http://www.alicebot.org/ http://www-ai.ijs.si/eliza-cgi-bin/eliza_script http://www.simonlaven.com/

44. Chat bots... Clip from New Scientist, March 11, 2006

45. Applied AI – the 20 questions game Check out : http://www.20q.net/

46. AI as ”rational agent” We will focus on general principles of rational agents and how to construct them. –We can define rational as ”achieving the best outcome” where we measure the outcome. Clearly defined and also general. –We don’t have to meddle with what is ”human”.

47. Fundamental issues in AI Representation –Facts about the world have to be represented in some way. Logic is one language that is used in AI. How should knowledge be structured? What is explicit, and what must be inferred? How to encode "rules" for inference so as to find information that is only implicitly known? How deal with incomplete, inconsistent, and probabilistic knowledge? Search –Many tasks can be viewed as searching a very large problem space for a solution. Use of heuristics and constraints. Inference –Some facts can be inferred from other facts. Learning –Learning is essential in an intelligent system. Planning –Starting with general facts about the world, about the effects of basic actions, about a particular situation, and a statement of a goal, generate a strategy for achieving the goal.

48. Some discussion Exercise 1.1: Define in your own words: (a) intelligence, (b) artificial intelligence, and (c) agent. (a) “1 a (1) : the ability to learn or understand or to deal with new or trying situations : also : the skilled use of reason (2) : the ability to apply knowledge to manipulate one's environment or to think abstractly as measured by objective criteria (as tests) … 5 : the ability to perform computer functions” (Merriam-Webster on-line dictionary)

49. Some discussion Exercise 1.1: Define in your own words: (a) intelligence, (b) artificial intelligence, and (c) agent. (a) “1 a (1) : the ability to learn or understand or to deal with new or trying situations : REASON; also : the skilled use of reason (2) : the ability to apply knowledge to manipulate one's environment or to think abstractly as measured by objective criteria (as tests) … 5 : the ability to perform computer functions” (Merriam-Webster on-line dictionary)

50. Some discussion Exercise 1.1: Define in your own words: (a) intelligence, (b) artificial intelligence, and (c) agent. (b) We define artificial intelligence as the study and construction of agent programs that perform well in a given environment, for a given agent architecture. mother mummy … Mix (Merriam-Webster on-line dictionary)

51. Some discussion Exercise 1.1: Define in your own words: (a) intelligence, (b) artificial intelligence, and (c) agent. (c) We define an agent as an entity that takes action in response to percepts from an environment. apply knowledge to manipulate one's environment or to think abstractly as measured by objective criteria (as tests) … 5 : the ability to perform computer functions” (Merriam-Webster on-line dictionary)

52. More discussion Exercise 1.10: Are reflex actions rational? Are they intelligent?

53. More discussion Exercise 1.10: Are reflex actions rational? Are they intelligent? Yes, they are rational. Intelligent? Well, thinking before removing your hand from a hot stove might be considered stupid. However, no reasoning is needed so perhaps it isn’t intelligent.