CSC 8520 Artificial Intelligence Course Details by ecg16852


									CSC 8520: Artificial Intelligence
       Course Details
• Paula Matuszek, Robin McEntire
• Student Questionnaire
• Snow
   – Contact sheet
• Course web page
   –   Home page,
   –   Syllabus
   –   Handing in Homework
   –   Academic Integrity
• Questions?
        Intelligent Systems Lab
• Mendel 156
• We will meet in here, and use the lab during class
• Your badge should also open the door, and you
  can work in here. (It may take a while to get this
  all working)
   – No other classes
   – Some other students
   – Files and settings will NOT remain
• PCs have Windows XP, Lisp. Will have Prolog
  and some other tools we will use
                  Musings on AI
• AI to me is a lot of things.
• The field can generally be viewed from two
   – The areas you're working in
      •   Planning
      •   Learning
      •   Natural Language Understanding
      •   Games
   – The techniques you use
      •   Search
      •   Knowledge Representation
      •   Inference
      •   Logic
                 Our Approach
• Following the book:
   – Tools and techniques
   – Some of the domains, depending on interest
• Working in the lab:
   – We will spend some part of most classes doing hands-
     on stuff. Trying out tools and applications, exploring
     what's out there, etc.
• AI is also FUN, exciting, always new. I hope to
  convey some of why.
• We will all get more out of this class if you speak
  up. I encourage questions and ideas and
  discussion in class.
            Class Background
• In order to help structure and focus the course, we
  need to have an idea of the interests and
  backgrounds of the members of the class.
• We will add to the class web page lists of
  interesting resources. Two major sources you
  should be aware of:
   – Our textbook is in extensive use, and there is a web
     page with many resources and links at
   – The American Association for Artificial Intelligence is
     the primary professional organization in the US for AI.
     Their web page at has many resources.
• The remaining slides of this presentation are
  modified from those of Professor Maria
  DesJardins, University of Maryland Baltimore
  County. The originals can be found at
Introduction to
    Chapter 1
        Big Questions
• Can machines think?
• And if so, how?
• And if not, why not?
• And what does this say about
  human beings?
• And what does this say about
  the mind?
                       What is AI?
• There are no crisp definitions
• Here’s one from John McCarthy, (He coined the phrase AI in
   1956) - see http://www.formal.Stanford.EDU/jmc/whatisai/)
Q. What is artificial intelligence?
A. It is the science and engineering of making intelligent
   machines, especially intelligent computer programs. It is
   related to the similar task of using computers to understand
   human intelligence, but AI does not have to confine itself to
   methods that are biologically observable.
Q. Yes, but 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.
      Other possible AI definitions
• AI is a collection of hard problems which can be solved
  by humans and other living things, but for which we
  don’t have good algorithmic solutions
   – e.g., understanding spoken natural language, medical
     diagnosis, circuit design, etc.
• AI Problem + Sound theory = Engineering problem
• Many problems used to be thought of as AI but are
  now considered not
   – e.g., compiling Fortran in 1955, symbolic mathematics in
     1965, image cleanup
        What’s easy and what’s hard?
• Easier: many of the high level tasks we usually associate
  with “intelligence” in people
   – e.g., Symbolic integration, proving theorems, playing
     chess, medical diagnosis, etc.
• Harder: tasks that lots of animals can do
   –   walking around without running into things
   –   catching prey and avoiding predators
   –   interpreting complex sensory information
   –   modeling the internal states of other animals from their behavior
   –   working as a team (e.g. with pack animals)
• What's the difference?
                 Current State
• Is AI a failure? Is AI dead?
• NO. AI is
   – pervasive
   – invisible
• There are no solved problems in AI. Why? Once
  they're solved they aren't AI any more.
                Foundations of AI
                     Science &
     Mathematics                  Philosophy

                    AI                 Biology

       Psychology   Cognitive      Linguistics
                       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.
• Cognitive Science: 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.
  Possible Approaches
        humans     Well

          GPS     Rational
Think              agents
                              AI tends to
                              work mostly
                              in this area
 Act      Eliza
 Think well                                humans    Well

• Develop formal models of         Think             Rational

  knowledge representation,                 Eliza
                                    Act             systems
  reasoning, learning,
  memory, problem solving, that
  can be rendered in algorithms.
• There is often an emphasis on
  a systems that are provably
  correct, and guarantee finding
  an optimal solution.
  Act well                                                humans   Well

                                                  Think            Rational

• For a given set of inputs, generate an         Act    Eliza

  appropriate output that is not necessarily
  correct but gets the job done.
• A heuristic (heuristic rule, heuristic method) is a rule of
  thumb, strategy, trick, simplification, or any other kind of
  device which drastically limits search for solutions in large
  problem spaces.
• Heuristics do not guarantee optimal solutions; in fact, they
  do not guarantee any solution at all: all that can be said
  for a useful heuristic is that it offers solutions which are
  good enough most of the time.
  – Feigenbaum and Feldman, 1963, p. 6
Think like humans                                humans   Well

                                         Think            Rational
• Cognitive science approach                               agents

• Focus not just on behavior and I/O Act Eliza     Heuristic
  but also look at reasoning process.
• Computational model should reflect "how" results
  were obtained.
• Provide a new language for expressing cognitive
  theories and new mechanisms for evaluating them
• GPS (General Problem Solver): Goal not just to
  produce humanlike behavior (like ELIZA), but to
  produce a sequence of steps of the reasoning
  process that was similar to the steps followed by a
  person in solving the same task.
Act like humans                                humans    Well

                                       Think             Rational

                                        Act     Eliza

• Behaviorist approach.
• Not interested in how you get results, just the
  similarity to what human results are.
• Exemplified by the Turing Test
  (Alan Turing, 1950).
                 Turing Test
• Three rooms contain a person, a computer, and an
• 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.
• ELIZA: A program that simulated a psychotherapist
  interacting with a patient and successfully "passed" the
  Turing Test.
• Coded at MIT during 1964-1966 by Joel Weizenbaum.
• First script was DOCTOR.
   – The script was a simple collection of syntactic patterns not unlike
     regular expressions
   – Each pattern had associated reply including bits of the input (after
     simple transformations (my -> your)
• Weizenbaum was shocked at reactions:
   – Psychiatrists thought it had potential.
   – People unequivocally anthropomorphised.
   – Many thought it solved the NL problem.
                    •   I am the psychotherapist. Please, describe your problems.
                        Each time you are finished talking, type RET twice.
  Eliza             •   i'm having a hard time with my students
                    •   Why do you say that?
• This is a         •   well, they keep asking me for money
  transcript of a   •   Maybe your plans have something to do with this.
  conversation      •   what plans?
                    •   Is it because of your life that you say what plans?
  with an Eliza-
                    •   No, it's because I didn't know what you were talking about
  like program      •   Is it because you didn't know what I was talking about that you
  found in              came to me?
  Emacs (Gnu        •   no, it's because i wanted to see if you could pass the turing test
  20.4.1)           •   Does it bother you that you wanted to see if I could really pass
                        the turing test?
• Try typing        •   …..
                    •   How do you reconcile problems at school?
  Meta-x            •   This is a waste of time. Good bye
  doctor            •   My secretary will send you a bill.
in your favorite
                             H: Good afternoon. My name is
Colby’s PARRY                    Doctor Jones.
                             P: Pleased to meet you.
• Kenneth Colby modeled
                             H: How are you?
  a paranoid using the
                             P: All right I guess.
  same techniques circa
                             H: Could you tell me your name?
                             P: Pat Smith.
• PARRY has basic            H: I though you might have some
  emotions. If it gets           problems.
  angry, its replies         P: I've been upset lately.
  become more hostile.       H: By what?
• In a Turing test, expert   P: People get on my nerves
  psychiatrists were             sometimes.
  unable to distinguish      H: Tell me more.
  PARRY’s ramblings          P: Do you know anything about
  from those of real             bookies?
  paranoids.                 ...
          The Loebner Contest
• A modern version of the Turing Test, held annually,
  with a $100,000 cash prize.
• Restricted topic (removed in 1995) and limited time.
• Participants include a set of humans and a set of
  computers and a set of judges.
• Scoring
   – Rank from least human to most human.
   – Highest median rank wins $2000.
   – If better than a human, win $100,000. (Nobody
So when WILL we decide that
  computers are intelligent?
How Do We Know When We're
• Some requirements I think any test we use must
   – Whatever test we use must not exclude the majority of
     adult humans. I can't play chess at a grand master
   – Whatever test we use must produce an observable
     result. "Isn't intelligent because it doesn't have a mind"
     is perhaps a topic for interesting philosophical debate,
     but it's not of any practical help.
         What can AI systems do
Here are some example applications
• Computer vision: face recognition from a large set
• Robotics: autonomous (mostly) car
• 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
• Games: Grand Master level in chess (world champion),
  checkers, etc.
   What can’t AI systems do yet?
• Understand natural language robustly (e.g., read
  and understand articles in a newspaper)
• Surf the web
• Interpret an arbitrary visual scene
• Learn a natural language
• Play Go well
• Construct plans in dynamic real-time domains
• Refocus attention in complex environments
• Perform life-long learning
  What's Happening Now in AI?
• Exercise for the next part of the class:
• In teams of two:
   – Log in to one of the workstations
   – Go to the AAAI news web page:
   – Explore some of the news articles on topics that interest
   – Pick two articles to tell us about at the end of the class.
     Why do those two interest you?
     First Homework Assignment
•    Assignment (link on the syllabus page).
1.   Read chapters 1 and 2. (Chapter 2 is what we will cover next week)
2.   From the textbook: Answer questions 1.2 and any three of 1.7a-j. Look at
     the other questions and think about them; you might find it interesting to
     make note of your thoughts and read them again at the end of the course. For
     question 1.2, you can fund a copy of Turing's paper at
3.   Skim through your textbook, including the detailed contents list. Choose two
     chapters from chapters 11-27 that you are most interested in seeing us cover
     in class.

Due: 5PM, Jan 22.

•    Academic Integrity revisited.

To top