Artificial Intelligence

1. Artificial Intelligence Introduction

2. AI • You are a caveman (or woman) • I travel back in time and bring you a LapTop and show you some of the things it is capable of doing. • Question : Would you, as a caveman, consider the computer to be intelligent?

3. Big questions • Can machines think? • If so, how? • If not, why not? • What does this say about humans? • What does this say about the mind?

4. AI Long Term Goals Produce intelligent behaviour in machines • Why use computers at all? • They can do things better than us • Big calculations quickly and reliably • We do intelligent things • So get computers to do intelligent things

5. Some Advantages of Artificial Intelligence • more powerful and more useful computers • new and improved interfaces • solving new problems • better handling of information • relieves information overload • conversion of information into knowledge

6. The Disadvantages • increased costs • difficulty with software development - slow and expensive • few experienced programmers • few practical products have reached the market as yet.

7. Some AI Systems that are Better Than Humans • Backgammon • TD gammon was the first program to beat the worlds best players (Gerald Tesauro) • http://researchweb.watson.ibm.com/massive/tdl.html

8. Why AI? • Engineering: To get machines to do a wider variety of useful things • e.g., understand spoken natural language, recognize individual people in visual scenes, find the best travel plan for your vacation, etc. • CognitiveScience: As a way to understand how natural minds and mental phenomena work • e.g., visual perception, memory, learning, language, etc. • Philosophy: As a way to explore some basic and interesting (and important) philosophical questions • e.g., the mind body problem, what is consciousness, etc.

9. What is Artificial Intelligence ? • making computers that think? • the automation of activities we associate with human thinking, like decision making, learning ... ? • the art of creating machines that perform functions that require intelligence when performed by people ?

10. What’s easy and what’s hard for AI? • It’s been easier to mechanize many of the high-level tasks we usually associate with “intelligence” in people • e.g., symbolic integration, proving theorems, playing chess, medical diagnosis • It’s been very hard to mechanize tasks that lots of animals can do • walking around without running into things • catching prey and avoiding predators • interpreting complex sensory information (e.g., visual, aural, …) • modeling the internal states of other animals from their behavior • working as a team (e.g., with pack animals) • Is there a fundamental difference between the two categories?

11. What can AI systems do? Here are some example applications • Computer vision: face recognition from a large set • Robotics: autonomous (mostly) automobile • Natural language processing: simple machine translation • Expert systems: medical diagnosis in a narrow domain • Spoken language systems: ~1000 word continuous speech • Planning and scheduling: Hubble Telescope experiments • Learning: text categorization into ~1000 topics • User modeling: Bayesian reasoning in Windows help (the infamous paper clip…) • Games: Grand Master level in chess (world champion), checkers, etc.

12. IBM’s Deep Blue versus Kasparov • On May 11, 1997, Deep Blue was the first computer program to beat reigning chess champion Kasparov in a 6 game match (2 : 1 wins, with 3 draws) • Massively parallel computation (259th most powerful supercomputer in 1997) • Evaluation function criteria learned by analyzing thousands of master games • Searched the game tree from 6-12 ply usually, up to 40 ply in some situations. • One ply corresponds to one turn of play.

13. Robotics Shakey (1966-1972) Cog (90s) Robocup Soccer (2000s) Kismet (late 90s, 2000s) Boss (2007)

14. How is it Currently Done? Crusher and, more recently, PerceptTOR

15. DARPA grand challenge

16. Stanley Robot Stanford Racing Team www.stanfordracing.org Next few slides courtesy of Prof. Sebastian Thrun, Stanford University

17. What About the DARPA Grand Challenge? • Autonomous Navigation in the Desert over a 132 mile course. • 5 Teams succeeded! • http://www.darpa.mil/grandchallenge05/gcorg/index.html • This was a monumental achievement in autonomous robotics • HOWEVER: This was not an unstructured environment! • GPS waypoints were carefully chosen, sometimes less than a meter apart.

18. Laser Terrain Mapping Sebastian Stanley Stanley’s Technology Path Planning Learning from Human Drivers Adaptive Vision Images and movies taken from Sebastian Thrun’s multimedia website.

19. SENSOR INTERFACE PERCEPTION PLANNING&CONTROL USER INTERFACE RDDF database Top level control Touch screen UI corridor pause/disable command Wireless E-Stop Laser 1 interface RDDF corridor (smoothed and original) driving mode Laser 2 interface Laser 3 interface road center Road finder Path planner Laser 4 interface laser map trajectory map VEHICLE INTERFACE Laser 5 interface Laser mapper vision map Camera interface Vision mapper Steering control obstacle list Radar interface Radar mapper Touareg interface vehicle state (pose, velocity) vehicle state Throttle/brake control GPS position UKF Pose estimation Power server interface vehicle state (pose, velocity) GPS compass IMU interface velocity limit Surface assessment Wheel velocity Brake/steering emergency stop heart beats Linux processes start/stop health status Process controller Health monitor power on/off data GLOBAL SERVICES Data logger File system Communication requests Communication channels clocks Inter-process communication (IPC) server Time server

21. Europa Hydrobot • http://www.resa.net/nasa/images/gem/HYDROBOT.JPG

22. AI Applications Games:

23. AI Applications • Games:

24. AI Applications • Robotic toys:

25. AI Applications • Transportation: • Pedestrian detection:

26. AI Applications • Medicine: • Image guided surgery

27. AI Applications • Autonomous Planning & Scheduling: • Telescope scheduling

28. Why is AI hard? Two usual ingredients (for standard AI) • Representation • need to represent our knowledge in computer readable form • Reasoning • need to be able to manipulate knowledge and derive new knowledge • many possible ways to do this, but most give rubbish • finding the successful way usually involves search Both of these are hard.

29. A C D B E The Travelling Salesman Problem (TSP) • A salesperson has to visit a number of cities • (S)He can start at any city and must finish at that same city • The salesperson must visit each city only once • For example, with 5 cities a possible tour is:

30. Combinatorial Explosion A 50 City TSP has 1.52 * 1064 possible solutions Age of the universe is 15 billion (1.5 * 1010) years There are 30 million seconds in a year Age of universe is about 45 * 1016 seconds A 10GHz computer might do 109 tours per second Running since start of universe, it would still only have done 1026 tours Not even close to evaluating all tours! Need to be clever about how to solve such search problems!

31. AI Generic Techniques • Automated Reasoning • Resolution, proof planning, Davis-Putnam, CSPs • Machine Learning • Neural nets, ILP, decision tree learning • Natural language processing • N-grams, parsing, grammar learning • Robotics • Planning, edge detection, cell decomposition • Evolutionary approaches • Crossover, mutation, selection

32. Course Overview: Three areas • AI fundamentals • Characterisations, terminology, methodologies • Representation and search • Application to game playing • Automated reasoning (deduction) • Socrates was mortal • Machine learning (induction) • Every man has died, so we all die

33. Some Famous Imitation Games • 1960s ELIZA • Rogerian psychotherapist • 1970s SHRDLU • Blocks world reasoner • 1980s NICOLAI • unrestricted discourse • 1990s Loebner prize • win $100,000 if you pass the test

34. The problem with ELIZA • Eliza used simple pattern matching • “Well, my friend made me come here” • “Yourfriend made you come here?” • Eliza written by Joseph Weizenbaum

35. Who does AI? • Academic researchers (perhaps the most Ph.D.-generating area of computer science in recent years) • Some of the top AI schools: CMU, Stanford, Berkeley, MIT, UIUC, UMd, U Alberta, UT Austin, ... (and, of course, Swarthmore!) • Government and private research labs • NASA, NRL, NIST, IBM, AT&T, SRI, ISI, MERL, ... • Lots of companies! • Google, Microsoft, Honeywell, Teknowledge, SAIC, MITRE, Fujitsu, Global InfoTek, BodyMedia, ...

36. The course topics • introduction to AI • AI application areas • Knowledge representation • Search space • Machine learning

37. Course overview • Introduction and Agents (chapters 1,2) • Search (chapters 3,4,5,6) • Logic (chapters 7,8,9) • Planning (chapters 11,12) • Uncertainty (chapters 13,14) • Learning (chapters 18,20) • Natural Language Processing (chapter 22,23)

38. AI definition AI is a branch of computer science and it concerned with intelligent behavior.

39. What is AI? • There are no crisp definitions Q. What is artificial intelligence? A. It is the science and engineering of making intelligent machines, especially intelligent computer programs. Q. what is intelligence? A. Intelligence is the computational part of the ability to achieve goals in the world. Varying kinds and degrees of intelligence occur in people, many animals and some machines.

40. What is Intelligence? • Intelligence: • “the capacity to learn and solve problems” (Websters dictionary) • in particular, • the ability to solve novel problems • the ability to act rationally • the ability to act like humans • Artificial Intelligence • build and understand intelligent entities or agents • 2 main approaches: “engineering” versus “cognitive modeling”

41. Success Stories • Deep Blue defeated the reigning world chess champion Garry Kasparov in 1997 • AI program proved a mathematical conjecture (Robbins conjecture) unsolved for decades • 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

42. Can Computers Talk? • This is known as “speech synthesis” • translate text to phonetic form • e.g., “fictitious” -> fik-tish-es • use pronunciation rules to map phonemes to actual sound • Difficulties • sounds made by this “lookup” approach sound unnatural • sounds are not independent • a harder problem is emphasis, emotion, etc • humans understand what they are saying • Conclusion: • NO,for complete sentences • YES, for individual words

43. Can Computers Recognize Speech? • Speech Recognition: • mapping sounds from a microphone into a list of words • classic problem in AI, very difficult • “Lets talk about how to wreck a nice beach” • (I really said “________________________”) • Recognizing single words from a small vocabulary • systems can do this with high accuracy (order of 99%)

44. Alan M Turing, Hero • Helped to found theoretical CS • 1936, before digital computers existed • Helped to found practical CS • wartime work decoding Enigma machines • ACE Report, 1946 • Helped to found practical AI • first (simulated) chess program • Helped to found theoretical AI …

45. Can Computers “see”? • Recognition v. Understanding (like Speech) • Recognition and Understanding of Objects in a scene • look around this room • you can effortlessly recognize objects • human brain can map 2d visual image to 3d “map” • Why is visual recognition a hard problem? • Conclusion: • mostly NO:computers can only “see” certain types of objects under limited circumstances • YES for certain constrained problems (e.g., face recognition)

46. What did Turing think? • Turing (in 1950) believed that by 2000 • computers available with 128Mbytes storage • programmed so well that interrogators have only a 70% chance after 5 minutes of being right • “By 2000 the use of words and general educated opinion will have altered so much that one will be able to speak of machines thinking without expecting to be contradicted”

47. Turing Test • Three rooms contain a person, a computer, and an interrogator. • The interrogator can communicate with the other two by teleprinter. • The interrogator tries to determine which is the person and which is the machine. • The machine tries to fool the interrogator into believing that it is the person. • If the machine succeeds, then we conclude that the machine can think.

48. The Imitation Game • Interrogator in one room • computer in another • person in a third room • From typed responses only (text-only), can interrogator distinguish between person and computer? • If the interrogator often guesses wrong, say the machine is intelligent.

49. Can Machines Think? • Turing starts by defining machine & think • Will not use everyday meaning of the words • otherwise we could answer by Gallup poll • Instead, use a different question • closely related, but unambiguous • “I believe the original question to be too meaningless to deserve discussion”

50. A sample game • Turing suggests some Q & A’s: • Q: Please write me a sonnet on the subject of the Forth Bridge • A: Count me out on this one, I never could write poetry • Q: Add 34957 to 70764. • (pause about 30 seconds) • A: 105621 • Q: Do you play chess? • A: Yes • Q: I have K at my K1, and no other pieces. You have only K at K6 and R at R1. It is your move. What do you play? • (pause about 15s) • A: R-R8 mate