Computer Science CPSC 422

1
Computer Science CPSC 422 Intelligent
Systems Cristina Conati
2
Super Brief Intro

• Advanced AI course
• Builds upon 322 (and 312)
• 322 gave a broad, high level overview of main
  research areas in AI (logic, search, planning,
  reasoning under uncertainty, decision making
• We will go into more depth on some of the topics
• Look at Learning
• Study some applications, in the field of
  Intelligent User Interfaces

3
Overview

• Administrivia
• Lets connect back to 322 what is AI?
• Refresher
• Examples

4
People

• Instructor
• Cristina Conati ( conati_at_cs.ubc.ca  office CICSR
  125)
• Teaching Assistant
• Sean Sutherland (ssuther_at_cs.ubc.ca)
• CWSEI PostDoc
• Frank Hutter

5
Course Pages

• Course website
• http//www.cs.ubc.ca/conati/422/422-2009World
  /422-2009.html
• This site also includes a calendar with a
  tentative scheduling of topics.
• http//www.cs.ubc.ca/conati/422/422-2009World/sch
  edule-422-2009.html
• CHECK IT OFTEN!
• Lecture slides
• Assignments/Solutions
• Other material

6
Course Material

• Main Textbook
• Artificial Intelligence A Modern Approach
  (AIMA). 2nd edition, Russell and Norvig, 2003
• Additional textbook Artificial Intelligence
  Foundations of Computational Agents. by Poole and
  Mackworth. (PM)
• This is the second edition of the textbook
  Computational Intelligence, by Poole Mackworth
  and Gobel.
• it's available electronically for free (via
  WebCT). Ill post the relevant chapters as needed
• This textbook is still under development, and it
  is not a substitute for the AIMA textbook

7
Course Material

• Lecture Slides
• I'll  post a version of each lecture's slides in
  advance (by midnight before that lecture), but
  the  version posted may not be the very final one
  that I will use in class. 
• However, I will make sure to  post the final
  version after class if there are substantial 
  changes/additions
• But I won't post  material that I write on the
  slides or on the board during class. You'll have
  to come to class to get that .
• You will need to know all the material in the
  readings for each class, regardless of whether it
  has been explicitly covered in class.
• You will also need to know all the material
  covered in class, whether or not it is included
  in the readings or available on-line.  

8
Readings

• It is strongly recommended that you read the
  assigned readings before each class. It will help
  you understand the material better when I lecture
• However, there will be some classes that are
  centered around the discussion of one or more
  research papers.
• You MUST read the papers before coming to class,
  because
• you will have to come up with questions on them
  and participate to class discussion (more on this
  later)

9
How to Get Help?

• Use the WebCT Discussion Board for questions on
  course material (so check it frequently)
• That way others can learn from your questions and
  comments
• Use email for personal questions (e.g., grade
  inquiries or health problems).
• Go to office hours (Discussion Board is NOT a
  good substitute for this) times below are still
  tentative, will be finalized next week
• Cristina likely Tu-Th, 330-430
• Sean TBA
• Can schedule by appointment if you have a class
  conflict with the official office hours

10
Getting Help from Other Students? (Plagiarism)

• It is OK to talk with your classmates about
  assignments learning from each other is good
• It is not OK, under any circumstances, to
• look at another student's solution (including
  solutions from assignments completed in the past)
  or previous sample solutions
• submit any solution not written by yourself,
• share your own work with others.
• Submit work done as part of an assignment for
  another course without the approval of all
  instructors involved.
• See UBC official regulations on what constitutes
  plagiarism (pointer in syllabus)
• Ignorance of the rules will not be a sufficient
  excuse for breaking them

11
Getting Help from Other Students? (Plagiarism)

• If you are in any doubt about the interpretation
  of any of these rules, please consult the
  instructor or the  TA!
• All cases of plagiarism will be severely dealt
  with by the Deans
• Office (thats the official procedure)
• So, it is better to skip an assignment than to
  have academic misconduct recorded on your
  transcript and additional penalties as serious as
  expulsion from the university

12
Evaluation

• Final exam (45)
• midterm exams (30)
• Assignments (15 )
• Class participation and questions for classes
  based on paper discussion (10)
• But, if your final grade is 20 higher than your
  midterm grade
• Midterm 15
• Final 60
• To pass at least 50 in both your overall grade
  and your final
• exam grade

13
Coursework Assignments

• To be handed via Handin by the appointed
  deadline.
• Late assignments will be graded as follows
  (unless the instructor specifies otherwise)
• If submitted after the lecture starts yet 
  before 430pm on the same day, you'll receive a
  penalty of 20
• If submitted by 2pm   the next day, you'll
  receive a penalty of 40.
• If submitted by 2pm  of the second day after the
  due date,  you'll receive a penalty of 60 .
• No late assignment will be accepted after that.
• You will have one Late Assignment Bonus, i.e. you
  will be allowed to submit one of the assignments
  up to 2 days late (i.e. by 2pm of the of the
  second day after the due date), with no penalty.
• See syllabus for details on how to submit late
  assignments

14
Coursework discussion-based classes

• Discussion-based classes
• There will be a few classes during the course
  that will be centered on reading and discussing
  one or more research papers
• You will have to
• come up with critical questions (discussion
  points) on each of the assigned readings (I will
  give you the exact number for each set of
  readings)
• Be prepared to present and discuss your questions
  in class
• Hand in a written version of your questions (Ill
  give you details on when and how to do this as we
  go)

15
Coursework discussion-based classes

• First discussion-based class next Tuesday
• Paper (available on-line from class schedule)
• Conati C., Gertner A., VanLehn K., 2002. Using
  Bayesian Networks to Manage Uncertainty in
  Student Modeling. User Modeling and User-Adapted
  Interaction. 12(4) p. 371-417.
• Make sure to have at least two questions on this 
  reading to  discuss  in class. 
• Send you questions to both conati_at_cs.ubc.ca and
  ssuther_at_cs.ubc.ca by 9am on Tuesday.

16
Questions on papers

• Clarification questions are welcome, but  there
  should be  at least two that can be used as
  discussion points, i.e. that
• Question elements of the presented research
  (i.e. point out weaknesses)
• make connections with the relevant techniques
  presented in class (Bnets in case of Tuesday
  paper)
• Make connections/comparisons with other papers
  (once we have covered enough papers to do this)

17
Missing Assignments or Exams

• If serious circumstances (like an illness or
  other personal matters)
• cause you to be late for an assignment or to miss
  an exam
• You'll need to provide a note from your doctor,
  psychiatrist, academic advisor, etc.
• If you miss an assignment, your score will be
  reweighed to exclude that assignment
• If you miss the midterm, those grades will be
  shifted to the final
• thus, your total grade will be 75 final, 25
  coursework
• If you miss the final, you'll have to write a
  make-up final as soon as possible

18
To Summarize

• All the course logistics are described in the
  course syllabus
• http//www.cs.ubc.ca/conati/422/422-2009World/422
  -2009.html
• Make sure to read it and that you agree with the
  course rules before deciding to take the course

19
Overview

• Administrivia
• Lets connect back to 322 what is AI?
• Refresher
• Examples

20
What is Artificial Intelligence?
From Russell S. and Norvig, P.Artificial
Intelligence A Modern Approach.'' 2nd Ed.,
Prentice Hall, 2003
21
Systems that act like humans

• Turing test (1950) Can a human interrogator tell
  whether (written) responses to her (written)
  questions come from a human or a machine?
• Natural Language Processing
• Knowledge Representation
• Automated Reasoning
• Machine Learning
• Total Turing Test (extended to include physical
  aspects of human behavior)
• Computer Vision
• Robotic

22
Has any AI System Passed the Tutoring Test?

• Not the full blown one (see http//www.loebner.net
  /Prizef/loebner-prize.html)
• It has a 100,000 and a Gold Medal for the first
  computer whose responses were indistinguishable
  from a human's.
• Each year an monetary prize and a bronze medal
  are awarded to the most human-like computer.
• The winner is the best entry relative to other
  entries that year, irrespective of how good it is
  in an absolute sense. E.g., (winner in 2008)
• Variations restricted to specific tasks requiring
  some form of intelligence

23
Winner in 2008Elbot From Artificial Solutions
The CSO Suite
24
Interactive Chat Assistant
The CSO Suite
25

• ALICE How are you doing today?
• Human not so good today, I have a
  headacheALICE Really you don't think so?Human
  what?ALICE Didn't you understand it?Human
  noALICE Which part are you confused
  about?Human I said that I had a headache and
  you answered "don't you think so"ALICE What did
  you mean by it? What happened to it?
• I am a philosophy professorALICE You are a
  philosophy professor? Is that your job?Human I
  am a physics professorALICE You are a physics
  professor? Does it pay well?

26
But why do we want an intelligent system to act
like a human?

• Because for many tasks, humans are still the Gold
  Standard

27
But why do we want an intelligent system to act
like a human?
28
Generating Multimedia Presentations

• Zhou, Wen, and Aggarwal. A Graph-Matching
  Approach to Dynamic Media Allocation
• in Intelligent Multimedia Interfaces. Best Paper
  Award at Intelligent User Interfaces 2005.

• Algorithm to effectively allocate text and
  graphics in multimedia presentations
• Empirical Validation
• System (RIA) output on 50 user queries (real
  estate and tourist guide application)
• Media allocation on same queries by two
  multimedia UI designers
• Third expert blindly ranked all responses
• Results
• RIA best/co-best in 17 cases
• Minor differences in 28 of the remaining 33 cases
  

29
Why Replicate Human Behavior, Including its
Limitations?

• AI and Entertainment
• E.g. Façade, a one-act interactive drama
  http//www.quvu.net/interactivestory.net/publicat
  ions
• Sometime these limitations can be useful
• E.g. Supporting Human Learning via Peer
  interaction (Goodman, B., Soller, A., Linton, F.,
  and Gaimari, R. (1997) Encouraging Student
  Reflection and Articulation using a Learning
  Companion. Proceedings of the AI-ED 97 World
  Conference on Artificial Intelligence in
  Education, Kobe, Japan, 151-158.)

30
What is Artificial Intelligence?
31
Systems That Think Like Humans

• Use Computational Models to Understand the Actual
  Workings of Human Mind
• Devise/Choose a sufficiently precise theory of
  the mind
• Express it as a computer program
• Check match between program and human behavior
  (actions and timing) on similar tasks
• Tight connections with Cognitive Science
• Also known as descriptive approaches to AI

32
Some Examples

• Newell and Simons GPS (General Problem Solver,
  1961) to test means-end approach as general
  problem solving strategy
• John Andersons ACT-R cognitive architecture
  (http//act-r.psy.cmu.edu/)
• Anderson, J. R. Lebiere, C. (1998). The atomic
  components of thought. Erlbaum
• Anderson, J. R., Bothell, D., Byrne, M. D.,
  Douglass, S., Lebiere, C., Qin, Y . (2004). An
  integrated theory of the mind. Psychological
  Review 111, (4). 1036-1060.
• SOAR cognitive architecture (http//sitemaker.umic
  h.edu/soar)
• Newell, A. 1990. Unified Theories of Cognition.
  Cambridge, Massachusetts Harvard University
  Press.

33
ACT-R Models for Intelligent Tutoring Systems
34
ACT-R Models for Intelligent Tutoring Systems
Intelligent Tutoring Systems (ITS)

• Intelligent agents that support human learning
  and training
• By autonomously and intelligently adapting to
  learners specific needs, like good teachers do

35
ACT-R Models for Intelligent Tutoring Systems

• One of ACT-R main assumptions
• Cognitive skills (procedural knowledge) are
  represented as production rules (IF this
  situation is TRUE, THEN do this)
• An ACT-R model representing expertise in a given
  domain requires writing a set of production
  rules mimicking how a human would reason to
  perform tasks in that domain
• Example solving algebraic equations
• An ACT-R model for an ITS encodes all the
  reasoning steps a student must go through to
  solve problems in the target domain
• Example rules describing how to solve
• 5x330

36
ACT-R Models for Intelligent Tutoring Systems

• Eq 5x330 Goals Solve for x
• Rule To solve for x when there is only one
  occurrence, unwrap (isolate) x.
• Eq5x330 Goals Unwrap x
• Rule To unwrap ?V, find the outermost wrapper ?W
  of ?V and remove ?W
• Eq 5x330 Goals Find wrapper ?W of x Remove
  ?W
• Rule To find wrapper ?W of ?V, find the top
  level expression ?E on side of equation
  containing ?V, and set ?W to part of ?E that does
  not contain ?V
• Eq 5x330 Goals Remove 3
• Rule To remove ?E, subtract ?E from both
  sides
• Eq 5x330 Goals Subtract 3 from both
  sides
• Rule To subtract ?E from both sides .
• Eq 5x3-330-3

37
Model Tracing

• Given a rule-based representation of a target
  domain (e.g. algebra),
• an expert model can trace student performance
  by firing rules and do a stepwise comparison of
  rule outcome with student action
• Mismatches signal incorrect student knowledge
  that requires tutoring
• Knowledge tracing extends model tracing to assess
  probability that a student knows domain rules
  given observed actions
• These models showed good fit with student
  performance, indicating value of the ACT-R theory
• Also, the Cognitive Tutors based on this model
  are great examples of AI success used in
  thousands of high schools in the USA
  (http//www.carnegielearning.com/success.cfm)

38
What is Artificial Intelligence?
39
Systems that Think Rationally

• Logic formalize right thinking, i.e.
  irrefutable reasoning processes.
• Logistic tradition in AI aims to build
  computational frameworks based on logic.
• Then use these frameworks to build intelligent
  systems
• You have seen some examples in 322 (Propositional
  Logic) and 312 (Logic Programming)
• We will look at more advanced logic-based
  representations
• Semantic Networks
• Ontologies

40
Systems that Think Rationally

• Main Research Problems/Challenges
• Proving Soundness and Completeness of various
  formalisms
• How to represent often informal and uncertain
  domain knowledge and formalize it in logic
  notation
• Computational Complexity
• Tradeoff between expressiveness and tractability
  in logic-based systems H. J. Levesque and R. J.
  Brachman. Expressiveness and tractability in
  knowledge representation and reasoning.
  Computational Intelligence, 3(2)78--93, 1987.

41
(No Transcript)
42
What is Artificial Intelligence?
43
Systems that Act Rationally

• The think rationally approach focuses on
  correct inference
• But more is needed for rational behavior, e.g.
• How to behave when there is no provably correct
  thing to do (i.e. reasoning under uncertainty)
• Fully reactive behavior (instinct vs. reason)

44
AI as Study and Design of Intelligent Agents

• An intelligent agent is such that
• Its actions are appropriate for its goals and
  circumstances
• It is flexible to changing environments and goals
• It learns from experience
• It makes appropriate choices given perceptual
  limitations and limited resources
• This definition drops the constraint of cognitive
  plausibility
• Same as building flying machines by understanding
  general principles of flying (aerodynamic) vs. by
  reproducing how birds fly
• Normative vs. Descriptive theories of Intelligent
  Behavior

45
Intelligent Agents

• In AI, artificial agents that have a physical
  presence in the world are usually known as Robots
  
• Robotics is the field primarily concerned with
  the implementation of the physical aspects of a
  robot (i.e. perception of the physical
  environment, actions on the environment)
• Another class of artificial agents include
  interface agents, for either stand alone or
  Web-based applications (e.g. intelligent desktop
  assistants, recommender systems, intelligent
  tutoring systems)
• Interface agents dont have to worry about
  interaction with the physical environment, but
  share all other fundamental components of
  intelligent behavior with robots
• We will focus on these agents in this course

46
Intelligent Agents in the World
Reasoning Decision Theory
Natural Language Understanding Computer
Vision Speech Recognition Physiological
Sensing Mining of Interaction Logs
47
The Act Rationally view

• This is the view that was adopted in cpsc322, and
  that we will
• continue to explore in the first part of the
  course
• Reasoning under uncertainty Bayesian networks
  and Hidden Markov Models
• Brief review, some applications, approximate
  inference
• Decision Making planning under uncertainty
• Markov Decision Processes, review
• Partially Observable Markov Decision Processes
  (POMDP)
• Learning
• Decision Trees, Neural Networks, Learning
  Bayesian Networks, Reinforcement Learning

48

• What is your job.
• What is YOUR job?
• I am physics professor
• What do you profess?
• I am a philosophy professor.
• What does 'dingus' have to do with philosophy?
• I am a nurse, what do I know
• Then why did you think that you knew what
  'dingus' means had anything to with philosophy?

49
JOAN WINNER OF THE 2006 PRIZE http//www.jabberwac
ky.com/

• Can you speak?
• Sure, what about you?
• No, I cannot.
• Why.
• Cause I don't know you.
• So if we get to know each other then you will be
  able to speak?
• Why is that not everyone is prepared to appeal
  only to the lowest common denominitator.
• I don't understand.
• I know you don't understand, I'll try to help
  you.
• How
• From talking with you.
• But you said you cannot speak.
• But you said you can't speak rot13?