CS 531: AI CS 331: Introduction to AI

1
CS 531 AI CS 331 Introduction to AI

• Dr Mian Muhammad Awais
• Room 416
• awais_at_lums.edu.pk
• Robotics and Intelligent Computing (RICE), Group

2
Course Description

• Course home page TBA
• Contactslecture notes, tutorials, assignment,
  grading, office hours, etc.
• Textbooks
• 1) Luger Artificial Intelligence Structures and
  Strategies for Complex Problem-solving Fourth
  Edition (Available as Reading package)
• 2) S. Russell and P. Norvig Artificial
  Intelligence A Modern Approach Prentice Hall,
  2003, First or Second Edition (HANDOUTS)
• Grading
• Quizzes (15)
• Practice (15),
• Midterm test (30)
• Final exam (40)
• Practice Options
• At least 2 Lab Assignments where attendance will
  be compulsory and will be taken.
• Critical reviews of interesting papers
• Take Home/In class Assignments (LISP/PROLOG)

3
TA Support/Office Hours

• TA 1 Umar Faiz (umerf_at_lums.edu.pk)
• Office hours (TBA, see the website)
• TA 2 TBA
• Instructor Office Hours (room 416)
• 3 to 4 PM Every day except Friday
• awais_at_lums.eu.pk

4
Course Outline (Core Areas)Very Basic

• Introduction and Problem Solving
• (Todays Lecture)
• Part I
• Knowledge Representation
• Part II
• Informed Search Methods
• Part III
• Planning / Reasoning/Expert Systems
• Part IV
• Learning

5
Course Outline (Specialized Areas)

• To be decide as the course progresses
• Some options are
• NLP
• Speech Processing
• (On going project at LUMS, 1.0 million, 3 years)
• Agent Technology
• (Submitted project, 5.9 million, 3 years)
• Imitative Learning
• (On going project at LUMS, 4.3 million, 3 years)
• Case Based Reasoning
• etc

6
Course Format

• Each Class 100 minutes not 75 minutes
• Core Areas
• Basic stuff,
• same as CS 331,
• will go through it quickly,
• tested with take home assignments,
• Midterm and finals will have at least 60 from
  the core areas.
• Special Areas
• High level brief discussion,
• tested with assignments, quizzes,
• maximum of 40 covered in exams

7
Book Chapters

• Book Chapters and articles will be announced as
  we go along
• Slides will be available at the website and in
  the commons folder
• Details to be announced later

8
Informal Feedback Mechanism LETS IMPROVE AS WE
MARCH

• Roughly Every Two Weeks an anonymous
  questionnaire will be circulated to evaluate the
  course
• Your comments will be welcomed to improve the
  course as we go along
• (DONOT WAIT TILL THE END)
• Course progress discussion

9
Questions
10

• TWO PURPOSES of AI.
• One is to use the power of computers to augment
  human thinking,
• just as we use motors to augment human or horse
  power. Robotics and expert systems are major
  branches of that.
• The other is to use a computer's artificial
  intelligence to understand how humans think.
• In a humanoid way. If you test your programs not
  merely by what they can accomplish, but how they
  accomplish it, they you're really doing cognitive
  science you're using AI to understand the human
  mind.
• Herbert Simon

11
AI Dimensions

• Modeling
• Thought process/reasoning vs. behavior/action

2) Evaluation Success according to human
standards vs. success according to an ideal
concept of intelligence rationality.
12
What is AI?

• Views of AI fall into four categories

13
Thinking humanly

• Can machines think like humans
• Requires scientific theories of internal
  activities of the brain, psychological
  experiments are required
• Studied in Cognitive Modeling

14

• Thinking humanly cognitive modeling
• 1960s "cognitive revolution" information-processi
  ng psychology
  
• Validation Requires
• Predicting and testing behavior of human subjects
  (top-down)
• Direct identification from neurological data
  (bottom-up)
• Cognitive Science and Cognitive Neuroscience
• Distinct from AI

15
Thinking humanly Some References

• Daniel C. Dennet. Consciousness explained.
• M. Posner (edt.) Foundations of cognitive science
• Francisco J. Varela et al. The Embodied Mind
• J.-P. Dupuy. The mechanization of the mind

16
Thinking rationally
Laws of Thought Can machines think rationally
Several Greek schools developed various forms of
logic notation and rules of derivation for
thoughts may or may not have proceeded to the
idea of mechanization
17
Thinking rationally

• Aristotle what are correct arguments/thought
  processes?
• Mathematics and Philosophy to Modern AI
• Problems
• Not all intelligent behavior is mediated by
  logical deliberation
• What is the purpose of thinking? What thoughts
  should I have?
• A reference
• Ivan Bratko, Prolog programming for artificial
  intelligence.

18
Acting humanly
Can machines behave like Humans? Why and
How is not important Do what ever you can
19
Acting humanly Turing Test

• Turing (1950) "Computing machinery and
  intelligence"
• Operational test for intelligent behavior the
  Imitation Game
• Predicted that by 2000, a machine might have a
  30 chance of fooling a lay person for 5 minutes
• Anticipated all major arguments against AI in
  following 50 years
• Suggested major components of AI knowledge,
  reasoning, language understanding, learning

20
(No Transcript)
21
Objections - Turning Test Most AI Programs Are
Not Flexible In Nature
May Not Be Able to Answer Emotional Questions
22
Chinese Room

•    
• The Turing Test was the first attempt at
  resolving the question of machine intelligence.
• It was a behavioral test, judging intelligence
  based not on inner processes, or faithfulness to
  neuronal structure, but purely on a computer's
  ability to verbally communicate.
• This approach elicited numerous objections
• Why should behaviour be the final test on
  intelligence
• How can behavior suffice if the internal
  mechanisms controlling it are nothing like a
  human being's?
• How can a conversation capture all of human
  intelligence?
• These questions essentially reduced themselves to
  the question of whether one could pass the Turing
  Test, that is, produce passable conversational
  speech, while still possessing no 'real'
  intelligence. This argument has been stated in
  numerous ways, but perhaps none more eloquent
  than
• John Searle's Chinese Room metaphor.
• http//psych.utoronto.ca/7Ereingold/courses/ai/

23
Searle Counter Example

• Imagine a room, with a man trapped inside. The
  man speaks no Chinese. Someone slips a piece of
  paper under the door with Chinese writing on it.
• Having puzzled over it for a moment, he notices
  that there is a book in the room titled "What to
  do if someone slides some Chinese writing under
  the door."
• The book, he finds, is actually an enormous set
  of instructions for producing new Chinese symbols
  based on what comes in. The rules instruct him on
  how to produce new Chinese symbols, based on the
  ones received. They are all if-then type
  statements describing a pattern in the text and
  the appropriate action or response.
• He follows these rules, using the piece of paper
  handed to him, and produces a new sheet, which he
  slides back under the door.
• The next day, another sheet comes in, he passes
  the completed sheet back out.
• Outside, the world is amazed that this room can
  actually understand Chinese, that the room is
  intelligent. Inside though, we know that the man
  understands no Chinese whatsoever!

24
Conclusion

• What Searle describes is a system that produces
  intelligent, meaningful output, in the absence of
  true understanding. If you accept this
  counter-example, then the Turing Test is doomed.
  The Chinese Room would pass the Turing test, even
  though it lacks understanding and intelligence.
  Searle's argument has, naturally, produced its
  own share of furious debate, and several strong
  counter-arguments have been levelled at it.

25
References

• http//psych.utoronto.ca/7Ereingold/courses/ai/ca
  che/chineser.htm
• http//psych.utoronto.ca/7Ereingold/courses/ai/ca
  che/searle.html
• http//consc.net/online2.html (best resource)

26
Acting rationally

• Can machines behave rationally
• Rational behavior doing the right thing
• The right thing that which is expected to
  maximize goal achievement, given the available
  information
• Doesn't necessarily involve thinking e.g.,
  blinking reflex but thinking should be in the
  service of rational action

27
What is AI?

• Views of AI fall into four categories

Our Focus is "ACTING RATIONALLY"
28
Rational Agents

• An agent is an entity that perceives and acts
• Every thing to be discussed should be taken in
  the context of
• RATIONAL AGENTS
• Abstractly, an agent is a function from percept
  histories to actions
• f P ? A
• For a given class of environments/tasks, Rational
  Agents sought best performance

29
LimitationsRational Agents

• Computational limitations make perfect
  rationality unachievable
• Design best program for given machine resources

References Michael Wooldridge. Reasoning about
rational agents.
30
Definition AI Systems

• Artificial Systems that behave rationally
• Or
• limited rationality

31
Other Aspects

• Read it yourself

32
Another Definition AI?

• Computer based solution of complex problems
  through the application of processes that are
  analogous to the
• Human Intelligence

More inclined towards acting and thinking humanly
CONTROVERSIAL ISSUE (How to define Intelligence?)
33
Intelligence

• Reasoning Learning

- Establishes Relationships - Perception and
Comprehension - Generalization Ability
- Memory/Differentiation Chair vs Table
Spoon vs Fork
Intelligent Beings Intelligent Systems
34
Intelligence

Manifestation of intelligence is through Behavior
35
AI Though GroupsStrong BelieversWeak Believers
36
Weak AI?Computation Consciousness

• Brain has ingredients that are
• Non - computational
• Simulating consciousness is not possible

Computational Non Computational BRAIN
37
Strong AI ?
Consciousness - is some complicated computation
Computers can achieve or even exceed all Human
Capacities once high computational speeds are
achieved
Brains Are Computers of MEAT?
38
Strong and Weak AI

• http//www.ecs.soton.ac.uk/harnad/Papers/Py104/se
  arle.comp.html

39
Scope of AI Based Techniques
Main focus Problems that do not have algorithmic
solutions, or are very complex Vague, uncertain
and poor-defined systems Systems with decision
- making problems
(Examples?)
40
Example Tasks

• Game Playing
• Rules are well defined
• algorithmic solutions are very complex
• Formalization is easy

• Automated Reasoning
• Theorem proving
• Formal logic/ knowledge representation.

Expert Systems Mimic experts such as doctors
41

• Natural Language Processing
• Computer learn human languages
• Machine Translation
• Speech Synthesis

• Planning And Robotics
• Artificial Pets.
• Efforts to make machines
• - Responsive
• - Flexible
• e.g., Path Planning

42
Summary AI?

• Innovative Extension of Philosophy
• Understand and BUILD intelligent entities
• Formal Origin after WWII
• Highly interdisciplinary
• Variety of subfields
• This course will discuss some of them

43
AI prehistory

• Philosophy Logic, methods of reasoning, mind as
  physical system foundations of learning,
  language, rationality
• Mathematics Formal representation and proof
  algorithms, computation, (un)decidability,
  (in)tractability, probability
• Economics Utility, decision theory
• Neuroscience Physical substrate for mental
  activity
• Psychology Phenomena of perception and motor
  control, experimental techniques
• Computer Building fast computers engineering
• Control theory Design systems that maximize an
  objective function over time
• Linguistics Knowledge representation, grammar

44
History of AI

• 1943 McCulloch Pitts Boolean circuit
  model of brain
• 1950 Turing's "Computing Machinery and
  Intelligence"
• 1956 Dartmouth meeting "Artificial
  Intelligence" adopted
• 195269 Look, Ma, no hands!
• 1950s Early AI programs, including Samuel's
  checkers program, Newell Simon's Logic
  Theorist, Gelernter's Geometry Engine
• 1965 Robinson's complete algorithm for logical
  reasoning
• 196673 AI discovers computational
  complexity Neural network research almost
  disappears
• 196979 Early development of knowledge-based
  systems
• 1980-- AI becomes an industry
• 1986-- Neural networks return to popularity
• 1987-- AI becomes a science
• 1995-- The emergence of intelligent agents

45
State of the art AI

• Deep Blue defeated the reigning world chess
  champion Garry Kasparov in 1997
• Proved a mathematical conjecture (Robbins
  conjecture) unsolved for decades
• No hands across America (driving autonomously 98
  of the time from Pittsburgh to San Diego)
• 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
  
• NASA's on-board autonomous planning program
  controlled the scheduling of operations for a
  spacecraft
• Proverb solves crossword puzzles better than most
  humans

46
First Reading Assignment(Write a Two Page
Summary on What you think AI is)Submission
Email the article to Instructor /TA by Friday
500 pm (or in folder submission_1 in Cs 531AI)

• Lugers
• Chapter One Introduction
• Other References
• Alexander Igors Impossible minds
• (Help Material Available in the Library)

47
Topics Covered Today

• Luger (Some of the discussion is from Stuart and
  Norvig)
• Part I
• Chapter 1
• Articles 1.1 to 1.4
• Practice
• Attempt Exercise Questions
• Especially Qs 1 to 7, 10 to 12