O slideshow foi denunciado.
Utilizamos seu perfil e dados de atividades no LinkedIn para personalizar e exibir anúncios mais relevantes. Altere suas preferências de anúncios quando desejar.

Class overview, intro to AI - Belief-optimal Reasoning for Cyber ...

1.509 visualizações

Publicada em

  • Your opinions matter! get paid for them! click here for more info... http://ishbv.com/surveys6/pdf
       Responder 
    Tem certeza que deseja  Sim  Não
    Insira sua mensagem aqui
  • I went from getting $3 surveys to $500 surveys every day!! learn more... ♣♣♣ http://ishbv.com/surveys6/pdf
       Responder 
    Tem certeza que deseja  Sim  Não
    Insira sua mensagem aqui
  • Seja a primeira pessoa a gostar disto

Class overview, intro to AI - Belief-optimal Reasoning for Cyber ...

  1. 1. CS B351: INTRO TO ARTIFICIAL INTELLIGENCE AND COMPUTER SIMULATION Instructor: Kris Hauser http://cs.indiana.edu/~hauserk 1
  2. 2. BASICS  Class web site  http://cs.indiana.edu/courses/b351  Textbook  S. Russell and P. Norvig  Artificial Intelligence: a Modern Approach  2nd edition or 3rd edition 2
  3. 3. BASICS  Instructor  Kris Hauser (hauserk@indiana.edu)  AIs  Mark Wilson (mw54@indiana.edu) 3
  4. 4. OFFICE HOURS  Kris Hauser  M,Th 11-12 in Info W 300  TAs  W 1-3 in Lindley 406 4
  5. 5. AGENDA  Intro to AI  Overview of class policies 5
  6. 6. INTRO TO AI 6
  7. 7. WHAT IS AI?  AI is the reproduction of human reasoning and intelligent behavior by computational methods 7
  8. 8. WHAT IS AI?  AI is an attempt of reproduction of human reasoning and intelligent behavior by computational methods 8
  9. 9. WHAT IS AI?  Discipline that systematizes and automates reasoning processes to create machines that: 9 Think like humans Think rationally Act like humans Act rationally
  10. 10.  The goal of AI is: to build machines that operate in the same way that humans think  How do humans think?  Build machines according to theory, test how behavior matches mind’s behavior  Cognitive Science  Manipulation of symbolic knowledge  How does hardware affect reasoning? Discrete machines, analog minds 10 Think like humans Think rationally Act like humans Act rationally
  11. 11.  The goal of AI is: to build machines that perform tasks that seem to require intelligence when performed by humans  Take a task at which people are better, e.g.:  Prove a theorem  Play chess  Plan a surgical operation  Diagnose a disease  Navigate in a building  and build a computer system that does it automatically  But do we want to duplicate human imperfections? 11 Think like humans Think rationally Act like humans Act rationally
  12. 12.  The goal of AI is: to build machines that make the “best” decisions given current knowledge and resources  “Best” depending on some utility function  Influences from economics, control theory  How do self-consciousness, hopes, fears, compulsions, etc. impact intelligence?  Where do utilities come from? 12 Think like humans Think rationally Act like humans Act rationally
  13. 13. WHAT IS INTELLIGENCE? “If there were machines which bore a resemblance to our bodies and imitated our actions as closely as possible for all practical purposes, we should still have two very certain means of recognizing that they were not real men. The first is that they could never use words, or put together signs, as we do in order to declare our thoughts to others… Secondly, even though some machines might do some things as well as we do them, or perhaps even better, they would inevitably fail in others, which would reveal that they are acting not from understanding, …” Discourse on the Method, by Descartes (1598-1650) 13
  14. 14. WHAT IS INTELLIGENCE?  Turing Test (c. 1950) 14
  15. 15. AN APPLICATION OF THE TURING TEST  CAPTCHA: Completely Automatic Public Turing tests to tell Computers and Humans Apart 15
  16. 16. CHINESE ROOM (JOHN SEARLE) 16
  17. 17. CAN MACHINES ACT/THINK INTELLIGENTLY?  Yes, if intelligence is narrowly defined as information processing AI has made impressive achievements showing that tasks initially assumed to require intelligence can be automated Each success of AI seems to push further the limits of what we consider “intelligence” 17
  18. 18. SOME ACHIEVEMENTS  Computers have won over world champions in several games, including Checkers, Othello, and Chess, but still do not do well in Go  AI techniques are used in many systems: formal calculus, video games, route planning, logistics planning, pharmaceutical drug design, medical diagnosis, hardware and software trouble- shooting, speech recognition, traffic monitoring, facial recognition, medical image analysis, part inspection, etc...  DARPA Grand Challenge: robotic car autonomously traversed 132 miles of desert  IBM’s Watson competes with Jeopardy champs  Some industries (automobile, electronics) are highly robotized, while other robots perform brain and heart surgery, are rolling on Mars, fly autonomously, …, but home robots still remain a thing of the future 18 18
  19. 19. CAN MACHINES ACT/THINK INTELLIGENTLY?  Yes, if intelligence is narrowly defined as information processing AI has made impressive achievements showing that tasks initially assumed to require intelligence can be automated  Maybe yes, maybe not, if intelligence cannot be separated from consciousness  Is the machine experiencing thought?  Strong vs. Weak AI 19
  20. 20. 20
  21. 21. BIG OPEN QUESTIONS  Is intelligent behavior just information processing? (Physical symbol system hypothesis)  If so, can the human brain solve problems that are inherently intractable for computers? Will a general theory of intelligence emerge from neuroscience?  In a human being, where is the interface between “intelligence” and the rest of “human nature”  Self-consciousness, emotions, compulsions  What is the role of the body? (Mind-body problem) 21
  22. 22. 22  AI contributes to building an information processing model of human beings, just as Biochemistry contributes to building a model of human beings based on bio-molecular interactions  Both try to explain how a human being operates  Both also explore ways to avoid human imperfections (in Biochemistry, by engineering new proteins and drug molecules; in AI, by designing rational reasoning methods)  Both try to produce new useful technologies  Neither explains (yet?) the true meaning of being human
  23. 23. MAIN AREAS OF AI  Knowledge representation (including formal logic)  Search, especially heuristic search (puzzles, games)  Planning  Reasoning under uncertainty, including probabilistic reasoning  Learning  Robotics and perception  Natural language processing 23 Search Knowledge rep.Planning Reasoning Learning Agent Robotics Perception Natural language ... Expert Systems Constraint satisfaction
  24. 24. BITS OF HISTORY  1956: The name “Artificial Intelligence” is coined  60’s: Search and games, formal logic and theorem proving  70’s: Robotics, perception, knowledge representation, expert systems  80’s: More expert systems, AI becomes an industry  90’s: Rational agents, probabilistic reasoning, machine learning  00’s: Systems integrating many AI methods, machine learning, natural language processing, reasoning under uncertainty, robotics again 24
  25. 25. SYLLABUS  Introduction to AI  Philosophy, history, agent frameworks  Search  Uninformed search, heuristic search, heuristics  Search applications (and variants)  Constraint satisfaction, planning, game playing, motion planning  Reasoning under uncertainty  Probability, planning under uncertainty, Bayesian networks, probabilistic inference, dynamic modeling  Intro to machine learning  Neural nets, decision tree learning, support vector machines, etc. 25
  26. 26. 26 B335 Robotics I400 B552 B553 Knowledge representation and learning B657 Computer Vision Biologically-inspired computing B659 I486 Q360 B651 Natural Language Processing E626 Game theory Q570 Topics in AI B551 S626 S675 B351
  27. 27. CAREERS IN AI  ‘Pure’ AI  Academia, industry labs  Applied AI  Almost any area of CS!  NLP, vision, robotics  Economics  Cognitive Science 27
  28. 28. AI REFERENCES  Conferences  IJCAI, ECAI, AAAI, NIPS  Journals  AI, Comp. I, IEEE Trans. Pattern Anal. Mach. Intel., IEEE Int. Sys., Journal of AIR  Societies  AAAI, SIGART, AISB  AI Magazine (Editor: IU’s David Leake) 28
  29. 29. CLASS POLICIES 29
  30. 30. PREREQUISITES  C211  I recommend:  Two semesters programming  Basic knowledge of data structures  Basic knowledge of algorithmic complexity 30
  31. 31. PROGRAMMING ASSIGNMENTS  Projects will be written in Python  Great for scripting  Peter Norvig, Director of Research at Google, and textbook author  Easy to learn  2 weeks for each assignment 31
  32. 32. GRADING  50% Homework  6 assignments - lowest score will be dropped  30% Final  20% Midterm 32
  33. 33. HOMEWORK POLICY  Due at end of class on due date  Typically Tuesdays  Extensions only granted in rare cases  Require advance notice except emergencies 33
  34. 34. ENROLLMENT  Add/drop deadline  No penalty: Sept 3  Late drop/add: Oct 27  Waitlist deadline: Sept 4 34
  35. 35. TAKEAWAYS  AI has many interpretations  Act vs. think, human-like vs. rational  Concept has evolved  ‘I’ has many interpretations  Turing test  Chinese room  AI success stories from each perspective 35
  36. 36. HOMEWORK  Register  Textbook  Survey  http://cs.indiana.edu/classes/b351  Readings: R&N Ch. 1, 2, 26 36

×