Recommandé
Contenu connexe
Similaire à Unit 1 ppt.pptx
Similaire à Unit 1 ppt.pptx (20)
Dernier
Dernier (20)
Unit 1 ppt.pptx
- 1. 1 Introduction to Artificial Intelligence Third Year Computer Engineering Bhalke A.P.
- 2. Content Introduction to Artificial Intelligence, Foundations of Artificial Intelligence, History of Artificial Intelligence, State of the Art, Risks and Benefits of AI, Intelligent Agents, Agents and Environments, Good Behavior: Concept of Rationality, Nature of Environments, Structure of Agents. 2
- 3. Why Study AI? AI makes computers more useful Intelligent computer would have huge impact on civilization AI cited as “field I would most like to be in” by scientists in all fields Computer is a good metaphor for talking and thinking about intelligence
- 4. Why Study AI? Turning theory into working programs forces us to work out the details AI yields good results for Computer Science AI yields good results for other fields Computers make good experimental subjects Personal motivation: mystery
- 5. What is artificial intelligence? Popular conception driven by science ficition Robots good at everything except emotions, empathy, appreciation of art, culture, … … until later in the movie. Perhaps more representative of human autism than of (current?) real robotics/AI “It is my belief that the existence of autism has contributed to [the theme of the intelligent but soulless automaton] in no small way.” [Uta Frith, “Autism”] Current AI is also bad at lots of simpler stuff! There is a lot of AI work on thinking about what others are thinking
- 6. Real AI A serious science. General-purpose AI like the robots of science fiction is incredibly hard Human brain appears to have lots of special and general functions, integrated in some amazing way that we really do not understand at all (yet) Special-purpose AI is more doable (nontrivial) E.g., chess/poker playing programs, logistics planning, automated translation, voice recognition, web search, data mining, medical diagnosis, keeping a car on the road, … … … …
- 7. Definitions of AI Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally focus on action avoids philosophical issues such as “is the system conscious” etc. • We will follow “act rationally” approach – Distinction may not be that important • acting rationally/like a human presumably requires (some sort of) thinking rationally/like a human, • humans much more rational anyway in complex domains if our system can be more rational than humans in some cases, why not?
- 8. What is the definition of AI? Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally
- 9. What is the definition of AI? Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally Bellman, 1978 “[The automation of] activities that we associate with human thinking, activities such as decision making, problem solving, learning”
- 10. What is the definition of AI? Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally Charniak & McDermott, 1985 “The study of mental faculties through the use of computational models”
- 11. What is the definition of AI? Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally Dean et al., 1995 “The design and study of computer programs that behave intelligently. These programs are constructed to perform as would a human or an animal whose behavior we consider intelligent”
- 12. What is the definition of AI? Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally Haugeland, 1985 “The exciting new effort to make computers think machines with minds, in the full and literal sense”
- 13. What is the definition of AI? Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally Kurzweil, 1990 “The art of creating machines that perform functions that require intelligence when performed by people”
- 14. What is the definition of AI? Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally Luger & Stubblefield, 1993 “The branch of computer science that is concerned with the automation of intelligent behavior”
- 15. What is the definition of AI? Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally Nilsson, 1998 “Many human mental activities such as writing computer programs, doing mathematics, engaging in common sense reasoning, understanding language, and even driving an automobile, are said to demand intelligence. We might say that [these systems] exhibit artificial intelligence”
- 16. What is the definition of AI? Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally Rich & Knight, 1991 “The study of how to make computers do things at which, at the moment, people are better”
- 17. What is the definition of AI? Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally Schalkoff, 1990 “A field of study that seeks to explain and emulate intelligent behavior in terms of computational processes”
- 18. What is the definition of AI? Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally Winston, 1992 “The study of the computations that make it possible to perceive, reason, and act”
- 19. What is Artificial Intelligence? Human-like (“How to simulate humans intellect and behavior on by a machine.) Mathematical problems (puzzles, games, theorems) Common-sense reasoning (if there is parking-space, probably illegal to park) Expert knowledge: lawyers, medicine, diagnosis Social behavior Rational-like: achieve goals, have performance measure
- 20. What is Artificial Intelligence Thought processes “The exciting new effort to make computers think .. Machines with minds, in the full and literal sense” (Haugeland, 1985) Behavior “The study of how to make computers do things at which, at the moment, people are better.” (Rich, and Knight, 1991)
- 21. The Turing Test (Can Machine think? A. M. Turing, 1950) Requires Natural language Knowledge representation Automated reasoning Machine learning (vision, robotics) for full test
- 22. What is AI? Turing test (1950) Requires: Natural language Knowledge representation automated reasoning machine learning (vision, robotics.) for full test Thinking humanly: Introspection, the general problem solver (Newell and Simon 1961) Cognitive sciences Thinking rationally: Logic Problems: how to represent and reason in a domain Acting rationally: Agents: Perceive and act
- 23. AI examples Common sense reasoning Tweety Yale Shooting problem Update vs revise knowledge The OR gate example: A or B - C Observe C=0, vs Do C=0 Chaining theories of actions Looks-like(P) is(P) Make-looks-like(P) Looks-like(P) ---------------------------------------- Makes-looks-like(P) ---is(P) ??? Garage-door example: garage door not included. Planning benchmarks 8-puzzle, 8-queen, block world, grid-space world Abduction: cambridge parking example
- 24. History of AI McCulloch and Pitts (1943) Neural networks that learn Minsky (1951) Built a neural net computer Darmouth conference (1956): McCarthy, Minsky, Newell, Simon met, Logic theorist (LT)- proves a theorem in Principia Mathematica-Russel. The name “Artficial Intelligence” was coined. 1952-1969 GPS- Newell and Simon Geometry theorem prover - Gelernter (1959) Samuel Checkers that learns (1952) McCarthy - Lisp (1958), Advice Taker, Robinson’s resolution Microworlds: Integration, block-worlds. 1962- the perceptron convergence (Rosenblatt)
- 25. History, continued 1966-1974 a dose of reality Problems with computation 1969-1979 Knowledge-based systems Weak vs. strong methods Expert systems: Dendral:Inferring molecular structures Mycin: diagnosing blood infections Prospector: recomending exploratory drilling (Duda). Roger Shank: no syntax only semantics 1980-1988: AI becomes an industry R1: Mcdermott, 1982, order configurations of computer systems 1981: Fifth generation 1986-present: return to neural networks Recent event: AI becomes a science: HMMs, planning, belief network
- 26. Abridged history of AI 1943 1950 1956 1952—69 1950s McCulloch & Pitts: Boolean circuit model of brain Turing's "Computing Machinery and Intelligence" Dartmouth meeting: "Artificial Intelligence" adopted Look, Ma, no hands! Early AI programs, including Samuel's checkers program, Newell & Simon's Logic Theorist, Gelernter's Geometry Engine Robinson's complete algorithm for logical reasoning AI discovers computational complexity Neural network research almost disappears Early development of knowledge-based systems AI becomes an industry Neural networks return to popularity AI becomes a science The emergence of intelligent agents 1965 1966—73 1969—79 1980-- 1986-- 1987-- 1995--
- 27. State of the art Deep Blue defeated the reigning world chess champion Garry Kasparov in 1997 Proved a mathematical conjecture (Robbins conjecture) unsolved for decades No hands across America (driving autonomously 98% of the time from Pittsburgh to San Diego) During the 1991 Gulf War, US forces deployed an AI logistics planning and scheduling program that involved up to 50,000 vehicles, cargo, and people NASA's on-board autonomous planning program controlled the scheduling of operations for a spacecraft Proverb solves crossword puzzles better than most humans DARPA grand challenge 2003-2005, Robocup
- 28. Components of an AI System An agent perceives its environment through sensors and acts on the environment through actuators. Human: sensors are eyes, ears, actuators (effectors) are hands, legs, mouth. Robot: sensors are cameras, sonar, lasers, ladar, bump, effectors are grippers, manipulators, motors The agent’s behavior is described by it function that maps percept to action.
- 29. Rationality A rational agent does the right thing (what is this?) A fixed performance measure evaluates the sequence of observed action effects on the environment
- 30. PEAS Use PEAS to describe task Performance measure Environment Actuators Sensors
- 31. PEAS Use PEAS to describe task environment Performance measure Environment Actuators Sensors Example: Taxi driver Performance measure: safe, fast, comfortable (maximize profits) Environment: roads, other traffic, pedestrians, customers Actuators: steering, accelerator, brake, signal, horn Sensors: cameras, sonar, speedometer, GPS, odometer, accelerometer, engine sensors
- 32. Environment Properties Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent
- 33. Environment Examples Environment Obse rvabl e Determ inistic Episodic Stati c Discret e Agent s Chess with a clock Chess without a clock Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent
- 34. Environment Examples Environment Obse rvabl e Determ inistic Episodic Stati c Discret e Agent s Chess with a clock Fully Strategi c Sequenti al Semi Discret e Multi Chess without a clock Fully Strategi c Sequenti al Stati c Discret e Multi Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent
- 35. Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obse rvabl e Determ inistic Episodic Stati c Discret e Agent s Chess with a clock Fully Strategi c Sequenti al Semi Discret e Multi Chess without a clock Fully Strategi c Sequenti al Stati c Discret e Multi Poker
- 36. Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obse rvabl e Determ inistic Episodic Stati c Discret e Agent s Chess with a clock Fully Strategi c Sequenti al Semi Discret e Multi Chess without a clock Fully Strategi c Sequenti al Stati c Discret e Multi Poker Partia l Strategi c Sequenti al Stati c Discret e Multi
- 37. Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obse rvabl e Determ inistic Episodic Stati c Discret e Agent s Chess with a clock Fully Strategi c Sequenti al Semi Discret e Multi Chess without a clock Fully Strategi c Sequenti al Stati c Discret e Multi Poker Partia l Strategi c Sequenti al Stati c Discret e Multi Backgammon
- 38. Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obse rvabl e Determ inistic Episodic Stati c Discret e Agent s Chess with a clock Fully Strategi c Sequenti al Semi Discret e Multi Chess without a clock Fully Strategi c Sequenti al Stati c Discret e Multi Poker Partia l Strategi c Sequenti al Stati c Discret e Multi Backgammon Fully Stochas tic Sequenti al Stati c Discret e Multi
- 39. Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obse rvabl e Determ inistic Episodic Stati c Discret e Agent s Chess with a clock Fully Strategi c Sequenti al Semi Discret e Multi Chess without a clock Fully Strategi c Sequenti al Stati c Discret e Multi Poker Partia l Strategi c Sequenti al Stati c Discret e Multi Backgammon Fully Stochas tic Sequenti al Stati c Discret e Multi Taxi driving Partia l Stochas tic Sequenti al Dyn amic Continu ous Multi
- 40. Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obse rvabl e Determ inistic Episodic Stati c Discret e Agent s Chess with a clock Fully Strategi c Sequenti al Semi Discret e Multi Chess without a clock Fully Strategi c Sequenti al Stati c Discret e Multi Poker Partia l Strategi c Sequenti al Stati c Discret e Multi Backgammon Fully Stochas tic Sequenti al Stati c Discret e Multi Taxi driving Partia l Stochas tic Sequenti al Dyn amic Continu ous Multi Medical diagnosis
- 41. Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obse rvabl e Determ inistic Episodic Stati c Discret e Agent s Chess with a clock Fully Strategi c Sequenti al Semi Discret e Multi Chess without a clock Fully Strategi c Sequenti al Stati c Discret e Multi Poker Partia l Strategi c Sequenti al Stati c Discret e Multi Backgammon Fully Stochas tic Sequenti al Stati c Discret e Multi Taxi driving Partia l Stochas tic Sequenti al Dyn amic Continu ous Multi Medical diagnosis Partia l Stochas tic Episodic Stati c Continu ous Single
- 42. Environment Examples ally observable ic / strategic Fully observable vs. parti Deterministic vs. stochast Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obse rvabl e Determ inistic Episodic Stati c Discret e Agent s Chess with a clock Fully Strategi c Sequenti al Semi Discret e Multi Chess without a clock Fully Strategi c Sequenti al Stati c Discret e Multi Poker Partia l Strategi c Sequenti al Stati c Discret e Multi Backgammon Fully Stochas tic Sequenti al Stati c Discret e Multi Taxi driving Partia l Stochas tic Sequenti al Dyn amic Continu ous Multi Medical diagnosis Partia l Stochas tic Episodic Stati c Continu ous Single Image analysis
- 43. Environment Examples Environment Obse rvabl e Determ inistic Episodic Stati c Discret e Agent s Chess with a clock Fully Strategi c Sequenti al Semi Discret e Multi Chess without a clock Fully Strategi c Sequenti al Stati c Discret e Multi Poker Partia l Strategi c Sequenti al Stati c Discret e Multi Backgammon Fully Stochas tic Sequenti al Stati c Discret e Multi Taxi driving Partia l Stochas tic Sequenti al Dyn amic Continu ous Multi Medical diagnosis Partia l Stochas tic Episodic Stati c Continu ous Single Image analysis Fully Determi nistic Episodic Semi Discret e Single Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs.
- 44. Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. Environment Obse rvabl e Determ inistic Episodic Stati c Discret e Agent s Chess with a clock Fully Strategi c Sequenti al Semi Discret e Multi Chess without a clock Fully Strategi c Sequenti al Stati c Discret e Multi Poker Partia l Strategi c Sequenti al Stati c Discret e Multi Backgammon Fully Stochas tic Sequenti al Stati c Discret e Multi Taxi driving Partia l Stochas tic Sequenti al Dyn amic Continu ous Multi Medical diagnosis Partia l Stochas tic Episodic Stati c Continu ous Single Image analysis Fully Determi nistic Episodic Semi Discret e Single Robot part picking
- 45. Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. Environment Obse rvabl e Determ inistic Episodic Stati c Discret e Agent s Chess with a clock Fully Strategi c Sequenti al Semi Discret e Multi Chess without a clock Fully Strategi c Sequenti al Stati c Discret e Multi Poker Partia l Strategi c Sequenti al Stati c Discret e Multi Backgammon Fully Stochas tic Sequenti al Stati c Discret e Multi Taxi driving Partia l Stochas tic Sequenti al Dyn amic Continu ous Multi Medical diagnosis Partia l Stochas tic Episodic Stati c Continu ous Single Image analysis Fully Determi nistic Episodic Semi Discret e Single Robot part picking Fully Determi nistic Episodic Semi Discret e Single
- 46. Environment Examples Full par Det stoc Epi Stat Dis con Sin Environment Obse rvabl e Determ inistic Episodic Stati c Discret e Agent s Chess with a clock Fully Strategi c Sequenti al Semi Discret e Multi Chess without a clock Fully Strategi c Sequenti al Stati c Discret e Multi Poker Partia l Strategi c Sequenti al Stati c Discret e Multi Backgammon y observable vs. Fully Stochas tic Sequenti al Stati c Discret e Multi tially observable Taxi driving Partia l Stochas tic Sequenti al Dyn amic Continu ous Multi erministic vs. hastic / strategic Medical diagnosis Partia l Stochas tic Episodic Stati c Continu ous Single sodic vs. sequential Image analysis ic vs. dynamic Fully Determi nistic Episodic Semi Discret e Single crete vs. Robot part picking tinuous Fully Determi nistic Episodic Semi Discret e Single Interactive English gle agent vs. tutor
- 47. Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. Environment Obse rvabl e Determ inistic Episodic Stati c Discret e Agent s Chess with a clock Fully Strategi c Sequenti al Semi Discret e Multi Chess without a clock Fully Strategi c Sequenti al Stati c Discret e Multi Poker Partia l Strategi c Sequenti al Stati c Discret e Multi Backgammon Fully Stochas tic Sequenti al Stati c Discret e Multi Taxi driving Partia l Stochas tic Sequenti al Dyn amic Continu ous Multi Medical diagnosis Partia l Stochas tic Episodic Stati c Continu ous Single Image analysis Fully Determi nistic Episodic Semi Discret e Single Robot part picking Fully Determi nistic Episodic Semi Discret e Single Interactive English tutor Partia l Stochas tic Sequenti al Dyn amic Discret e Multi
- 48. Agent Types Types of agents (increasing in generality and ability to handle complex environments) Simple reflex agents Reflex agents with state Goal-based agents Utility-based agents Learning agent
- 49. Simple Reflex Agent Use simple “if then” rules Can be short sighted SimpleReflexAgent(percept) state rule = InterpretInput(percept) = RuleMatch(state, rules) action = RuleAction(rule) Return action
- 50. Example: Vacuum Agent Performance? 1 point for each square cleaned in time T? #clean squares per time step - #moves per time step? Environment: vacuum, dirt, multiple areas defined by square regions Actions: left, right, suck, idle Sensors: location and contents [A, dirty] Rational is not omniscient Environment may be partially observable Rational is not clairvoyant Environment may be stochastic Thus Rational is not always successful
- 51. Reflex Vacuum Agent If status=Dirty then return Suck else if location=A then return Right else if location=B then right Left
- 52. Reflex Agent With State Store previously- observed information Can reason about unobserved aspects of current state ReflexAgentWithState(percept) state rule = UpdateDate(state,action,percept) = RuleMatch(state, rules) action = RuleAction(rule) Return action
- 53. Reflex Vacuum Agent If status=Dirty then Suck else if have not visited other square in >3 time units, go there
- 54. Goal-Based Agents Goal reflects desires of agents May project actions to see if consistent with goals Takes time, world may change during reasoning
- 55. Utility-Based Agents Evaluation function to measure utility f(state) -> value Useful for evaluating competing goals
- 56. Learning Agents
- 57. Xavier mail delivery robot Performance: Completed tasks Environment: See for yourself Actuators: Wheeled robot actuation Sensors: Vision, sonar, dead reckoning Reasoning: Markov model induction, A* search, Bayes classification
- 58. Other Example AI Systems Knowledge Representation Search Problem solving Planning Machine learning Natural language processing Uncertainty reasoning Computer Vision Robotics
- 59. Some AI videos Note: there is a lot of AI that is not quite this “sexy” but still very valuable! E.g. logistics planning – DARPA claims that savings from a single AI planning application during 1991 Persian Gulf crisis more than paid back for all of DARPA’s investment in AI, ever. [Russell and Norvig] http://www.youtube.com/watch?v=1JJsBFiXGl0&feature=related http://www.youtube.com/watch?v=ICgL1OWsn58&feature=relate d http://www.cs.utexas.edu/~kdresner/aim/video/fcfs-insanity.mov http://www.youtube.com/watch?v=HacG_FWWPOw&feature=rela ted http://videolectures.net/aaai07_littman_ai/ http://www.ai.sri.com/~nysmith/videos/SRI_AR-PA_AAAI08.avi http://www.youtube.com/watch?v=ScXX2bndGJc
- 60. Thank You!!! 60