course overview and introduction
play

Course Overview and Introduction CE417: Introduction to Artificial - PowerPoint PPT Presentation

Course Overview and Introduction CE417: Introduction to Artificial Intelligence Sharif University of Technology Spring 201 8 Soleymani Some slides have been adopted from: - Klein and Abdeel, CS188, UC Berkeley. - Sandholm, 15381, CMU. Course


  1. Course Overview and Introduction CE417: Introduction to Artificial Intelligence Sharif University of Technology Spring 201 8 Soleymani Some slides have been adopted from: - Klein and Abdeel, CS188, UC Berkeley. - Sandholm, 15381, CMU.

  2. Course Info  Instructor: M. Soleymani  Email: soleymani@sharif.edu  HeadTA: Maryam Gholamalitabar 2

  3. Text Book Artificial Intelligence:A Modern Approach by Stuart Russell and Peter Norvig 3 rd Edition, 2009 http://aima.cs.berkeley.edu/ 3

  4. Marking Scheme  Mid Term Exam: 25%  Final Exam: 35%  Homeworks (written & programming): 35%  Four or five quizzes: 5% 4

  5. Today  What is artificial intelligence?  What can AI do?  What is this course? 5

  6. Sci-Fi AI? 6

  7. Formal Definitions of Artificial Intelligence Human intelligence Rational Thinking Thinking humanly Thinking rationally Behavior Acting humanly Acting rationally 7

  8. What is AI? The science of making machines that: Think like people Think rationally Act like people Act rationally 8

  9. What is AI? The science of making machines that: Think like people Think rationally Act like people Act rationally 9

  10. Acting Humanly  Turing Test (Turing, 1950): Operational test for intelligent behavior:  A human interrogator communicates (through a teletype) with a hidden subject that is either a computer system or a human. If the human interrogator cannot reliably decide whether or not the subject is a computer, the computer is said to have passed theTuring test.  5 minutes test, it passes by fooling the interrogator 30% of time  Turing predicted that by 2000 a computer could pass the test.  He was wrong. 10

  11. Rational Decisions We ’ ll use the term rational in a very specific, technical way:  Rational: maximally achieving pre-defined goals  Rationality only concerns what decisions are made (not the thought process behind them)  Goals are expressed in terms of the utility of outcomes  Being rational means maximizing your expected utility A better title for this course would be: Computational Rationality 11

  12. Maximize Your Expected Utility 12

  13. What About the Brain?  Brains (human minds) are very good at making rational decisions, but not perfect  Brains aren ’ t as modular as software, so hard to reverse engineer!  “ Brains are to intelligence as wings are to flight ”  Lessons learned from the brain: memory and simulation are key to decision making 13

  14. A (Short) History of AI Demo: HISTORY – MT1950.wmv 14

  15. A (Short) History of AI 1940-1950: Early days  1943: McCulloch & Pitts: Boolean circuit model of brain  1950: Turing's “ Computing Machinery and Intelligence ”  1950 — 70: Excitement: Look, Ma, no hands!  1950s: Early AI programs, including Samuel's checkers program, Newell  & Simon's Logic Theorist, Gelernter's Geometry Engine 1956: Dartmouth meeting: “ Artificial Intelligence ” adopted  1965: Robinson's complete algorithm for logical reasoning  1970 — 90: Knowledge-based approaches  1969 — 79: Early development of knowledge-based systems  1980 — 88: Expert systems industry booms  1988 — 93: Expert systems industry busts: “ AI Winter ”  1990 — : Scientific method (Statistical approaches)  Resurgence of probability, focus on uncertainty  General increase in technical depth  Agents and learning systems … “ AI Spring ” ?  2000 — :Where are we now?  15

  16. Birth of AI: 1943-1956 16

  17. A (Short) History of AI 1940-1950: Early days  1943: McCulloch & Pitts: Boolean circuit model of brain  1950: Turing's “ Computing Machinery and Intelligence ”  1950 — 70: Excitement: Look, Ma, no hands!  1950s: Early AI programs, including Samuel's checkers program, Newell  & Simon's Logic Theorist, Gelernter's Geometry Engine 1956: Dartmouth meeting: “ Artificial Intelligence ” adopted  1965: Robinson's complete algorithm for logical reasoning  1970 — 90: Knowledge-based approaches  1969 — 79: Early development of knowledge-based systems  1980 — 88: Expert systems industry booms  1988 — 93: Expert systems industry busts: “ AI Winter ”  1990 — : Scientific method (Statistical approaches)  Resurgence of probability, focus on uncertainty  General increase in technical depth  Agents and learning systems … “ AI Spring ” ?  2000 — :Where are we now?  17

  18. Early successes: 1950s-1960s -> A* algorithm 18

  19. First AI Winter: Late 1970s 19

  20. A (Short) History of AI 1940-1950: Early days  1943: McCulloch & Pitts: Boolean circuit model of brain  1950: Turing's “ Computing Machinery and Intelligence ”  1950 — 70: Excitement: Look, Ma, no hands!  1950s: Early AI programs, including Samuel's checkers program, Newell  & Simon's Logic Theorist, Gelernter's Geometry Engine 1956: Dartmouth meeting: “ Artificial Intelligence ” adopted  1965: Robinson's complete algorithm for logical reasoning  1970 — 90: Knowledge-based approaches  1969 — 79: Early development of knowledge-based systems  1980 — 88: Expert systems industry booms  1988 — 93: Expert systems industry busts: “ AI Winter ”  1990 — : Scientific method (Statistical approaches)  Resurgence of probability, focus on uncertainty  General increase in technical depth  Agents and learning systems … “ AI Spring ” ?  2000 — :Where are we now?  20

  21. Expert Systems and Business (1970s-1980s) 21

  22. A (Short) History of AI 1940-1950: Early days  1943: McCulloch & Pitts: Boolean circuit model of brain  1950: Turing's “ Computing Machinery and Intelligence ”  1950 — 70: Excitement: Look, Ma, no hands!  1950s: Early AI programs, including Samuel's checkers program, Newell  & Simon's Logic Theorist, Gelernter's Geometry Engine 1956: Dartmouth meeting: “ Artificial Intelligence ” adopted  1965: Robinson's complete algorithm for logical reasoning  1970 — 90: Knowledge-based approaches  1969 — 79: Early development of knowledge-based systems  1980 — 88: Expert systems industry booms  1988 — 93: Expert systems industry busts: “ AI Winter ”  1990 — : Scientific method (Statistical approaches)  Resurgence of probability, focus on uncertainty  General increase in technical depth  Agents and learning systems … “ AI Spring ” ?  2000 — :Where are we now?  22

  23. Focus on Applications (1990s-2010s) 23

  24. Reemergence of AI (2010s-??) 2015-2017 – superhuman speech understanding 24

  25. Current Applications of AI 25

  26. Superhuman strategic reasoning under imperfect information Libratus beats best humans at heads-up no-limit Texas hold ’ em poker [Brown & Sandholm] Pittsburgh, January 2017 Haikou, April 2017 26

  27. 27

  28. 28

  29. 29

  30. 30

  31. 31

  32. 32

  33.  AI is a fast-moving exciting area  We can directly make the world a better place 33

  34. What Can AI Now Do? Quiz:Which of the following can be done at present? Play a decent game of table tennis?  Play a decent game of Jeopardy?  Drive safely along a curving mountain road?  Drive safely alongTelegraph Avenue?  Buy a week's worth of groceries on the web?  Buy a week's worth of groceries at Berkeley Bowl?  Discover and prove a new mathematical theorem?  Converse successfully with another person for an hour?  Perform a surgical operation?  Put away the dishes and fold the laundry?  Translate spoken Chinese into spoken English in real time?  Write an intentionally funny story?  34

  35. Natural Language  Speech technologies (e.g. Siri) Automatic speech recognition (ASR)  Text-to-speech synthesis (TTS)  Dialog systems  35

  36. Natural Language  Speech technologies (e.g. Siri) Automatic speech recognition (ASR)  Text-to-speech synthesis (TTS)  Dialog systems   Language processing technologies Question answering  Machine translation  Web search  Text classification, spam filtering, etc …  36

  37. Vision (Perception)  Object and face recognition  Scene segmentation  Image classification Images from Erik Sudderth (left), wikipedia (right) 37

  38. Robotics  Robotics Part mech. eng.  Part AI  Reality much  harder than simulations!  Technologies Vehicles  Rescue  Soccer!  Lots of automation …   In this class: We ignore mechanical aspects  Methods for planning  Methods for control  Images from UC Berkeley, Boston Dynamics, RoboCup, Google 38

  39. Logic  Logical systems  Theorem provers  NASA fault diagnosis  Question answering  Methods:  Deduction systems  Constraint satisfaction  Satisfiability solvers (huge advances!) Image from Bart Selman 39

Recommend


More recommend