cs480/580 introduction to artificial intelligence shuiwang ji

Download CS480/580 Introduction to Artificial Intelligence Shuiwang Ji

If you can't read please download the document

Post on 19-Dec-2015

219 views

Category:

Documents


0 download

TRANSCRIPT

  • Slide 1
  • CS480/580 Introduction to Artificial Intelligence Shuiwang Ji
  • Slide 2
  • General information u Instructor: Shuiwang Ji Office hours: Monday and Wednesday, 4:30PM- 5:30PM, or by appointment Office location: E&CS 3204 E-mail: [email protected]@cs.odu.edu Research interests: machine learning, data mining, computer vision, computational biology u Course Homepage: http://www.cs.odu.edu/~sji/classes/fall2010/AI/ http://www.cs.odu.edu/~sji/classes/fall2010/AI/ 2
  • Slide 3
  • Textbooks u Main text: Artificial Intelligence: A Modern Approach, 3rd Edition, by Stuart Russell and Peter Norvig http://aima.cs.berkeley.edu/ u LISP programming: Practical Common Lisp by Peter Seibel http://www.gigamonkeys.com/book/ Other LISP books also work 3
  • Slide 4
  • Grading u Graduates and undergraduates will be graded separately u Homework: Undergraduate (30%): there will be 4-5 homework Graduate: (25%): there will be 3-4 homework u Term paper (5%): ONLY for graduate students u Project (30%): there will be 2-3 projects u Exam (40%): Exam 1: 10% Exam 2: 10% Final exam 20% 4 All homework and projects are strictly individual
  • Slide 5
  • LISP programming u Projects will involve LISP programming u Use Lisp-in-a-box (link from the class page) u Easy to install and use u A free book on LISP is available u Partial code will ONLY be provided in LISP u Need LISP tutorial lecture? 5
  • Slide 6
  • Project grading u Partial code in LISP will be provided u Students are asked to program the core algorithms u Some example inputs will be given, and the outputs and analysis are graded u Grading criteria General structure: 10% Project report: 30% Correctness: 60% 6
  • Slide 7
  • Course overview u Intelligent agent architecture u Problem-solving by searching u Constraint satisfaction problems (CSP) u Propositional logic u First-order logic u Probabilistic inference and Bayesian networks u Planning and Markov decision processes (MDP) u Machine learning 7
  • Slide 8
  • Class homepage u The class is temporally run through the homepage: http://www.cs.odu.edu/~sji/classes/fall2010/AI http://www.cs.odu.edu/~sji/classes/fall2010/AI u Switch to blackboard later on u Not hardcopy handouts, check class homepage/blackboard regularly 8
  • Slide 9
  • What is AI? 9
  • Slide 10
  • Two central questions 10 Humanly or rationally Thinking or acting Rational: does the right thing given what is knows
  • Slide 11
  • Definitions of AI 11 Humanly or rationally Thinking or acting
  • Slide 12
  • Think humanly: cognitive science 12 Do we want a machine that beats humans in chess or a machine that thinks like humans while beating humans in chess? DeepBlue supposedly DOESNT think like humans
  • Slide 13
  • Think rationally: law of thought 13 1.Not easy to take informal knowledge and state it in the formal terms required by logical notation 2.Reasoning on real-world problems is computationally demanding
  • Slide 14
  • Acting humanly: The Turing test 14 Mechanical flight became possible only when people decided to stop emulating birds Natural language processing Knowledge representation Automated reasoning Machine learning Natural language processing Knowledge representation Automated reasoning Machine learning
  • Slide 15
  • Acting rationally: rational agent 15 Making correct inference is sometimes part of being a rational agent Correct inference is not all of rationality There are ways of acting rationally that cannot be said to involve inference Making correct inference is sometimes part of being a rational agent Correct inference is not all of rationality There are ways of acting rationally that cannot be said to involve inference
  • Slide 16
  • The rational agent approach 16 Think humanlyThink rationally Acting humanly Acting rationally Humanly or rationally Thinking or acting
  • Slide 17
  • Rational agent 17
  • Slide 18
  • AI prehistory 18
  • Slide 19
  • Why AI? 19
  • Slide 20