CS 561: Artificial Intelligence

1
CS 561 Artificial Intelligence

• Instructor Prof. Hadi Moradi, moradi_at_usc.edu
• Lectures M-Th 0900-1040, OHE122
• Office hours TTH 230 400 pm, SAL310,
• Or by appointment
• Class format two sections of 45 minutes

2
CS 561 Artificial Intelligence

• Course web page
• http//www-scf.usc.edu/csci561a
• Up to date information, lecture notes
• Relevant dates, links, etc.
• Also you may check http//learn.usc.edu
• TAs Xiaoming Zheng
• SAL 237 (tel [phone])
• Office hours Monday, Wed., Thursday 1100-1200
• Email xiaominz_at_usc.edu
• Course material
• AIMA Artificial Intelligence A Modern
  Approach, by Stuart Russell and Peter Norvig. 2nd
  edition

3
CS 561 Artificial Intelligence

• Course overview foundations of symbolic
  intelligent systems. Agents, search, problem
  solving, logic, representation, reasoning,
  symbolic programming, probabilistic reasoning,
  and robotics.
• Prerequisites CS 455x, i.e.,
• programming principles, discrete mathematics for
  computing, software design and software
  engineering concepts. Some knowledge of C/C
  for some programming assignments.

4
CS 561 Artificial Intelligence

• Grading
• 25 for midterm
• 25 for final
• 40 for homeworks and projects
• 10 for Quizzes

5
Practical issues

• Class list use learn.usc.edu
• Login with your USC username and password
• If CSCI561A is not listed as your courses, notify
  the TA.
• Submissions See class web page under
  Assignmentssubmit -user csci561 -tag HW3
  HW3.tar.gz

6
Administrative Issues

• Midterm 1 7/27/09 1100 - 1240pm
• Midterm 2 8/11/09 1100 - 1240pm
• See also the class web page
• http//learn.usc.edu/

7
Why study AI?
Search engines
Science
Medicine/ Diagnosis
Labor
What else?
Appliances
8
Humanoid Robots From Honda to Sony
Walk
Turn
http//world.honda.com/robot/
Stairs
9
Sony AIBO
movie1
http//www.aibo.com
10
Natural Language Question Answering
http//www.ai.mit.edu/projects/infolab/
http//aimovie.warnerbros.com
11
Robot Teams
USC robotics Lab
12
What is AI?
The exciting new effort to make computers thinks
machine with minds, in the full and literal
sense (Haugeland 1985)
The study of mental faculties through the use of
computational models (Charniak et al. 1985)
The art of creating machines that perform
functions that require intelligence when
performed by people (Kurzweil, 1990)
A field of study that seeks to explain and
emulate intelligent behavior in terms of
computational processes (Schalkol, 1990)
Systems that think rationally
Systems that think like humans
Systems that act rationally
Systems that act like humans
13
AI The Bigger Picture
?
Computer Science
Philosophy
Artificial Intelligence
Cognitive Science (Psychology)
Robotics (Engineering)
Neuroscience (Biology)
?
14
Acting Humanly The Turing Test

• Alan Turing's 1950 article Computing Machinery
  and Intelligence discussed conditions for
  considering a machine to be intelligent
• Can machines think? ?? Can machines behave
  intelligently?
• The Turing test (The Imitation Game) Operational
  definition of intelligence.

15
Acting Humanly The Turing Test

• Computer needs to possesNatural language
  processing, Knowledge representation, Automated
  reasoning, and Machine learning
• Are there any problems/limitations to the Turing
  Test?

16
What tasks require AI?

• AI is the science and engineering of making
  intelligent machines which can perform tasks that
  require intelligence when performed by humans
• What tasks require AI?

17
What tasks require AI?

• Tasks that require AI
• Solving a differential equation
• Brain surgery
• Inventing stuff
• Playing Jeopardy
• Playing Wheel of Fortune
• What about walking?
• What about grabbing stuff?
• What about pulling your hand away from fire?
• What about watching TV?
• What about day dreaming?

18
Acting Humanly The Full Turing Test

• Problem
• 1) Turing test is not reproducible,
  constructive, and amenable to mathematic
  analysis.
• 2) What about physical interaction with
  interrogator and environment?

19
Acting Humanly The Full Turing Test

• Problem
• 1) Turing test is not reproducible,
  constructive, and amenable to mathematic
  analysis.
• 2) What about physical interaction with
  interrogator and environment?

Trap door
20
What would a computer need to pass the Turing
test?

• Communication Natural language processing
• Memory Knowledge representation
• Reasoning Automated reasoning
• Learning Machine learning

21
What would a computer need to pass the Turing
test?

• Sensing
• Vision (for Total Turing test) to recognize the
  examiners actions and various objects presented
  by the examiner.
• Other senses (total test) such as audition,
  smell, touch, etc.
• Motor control (total test) to act upon objects
  as requested.

22
Thinking Humanly Cognitive Science

• 1960 Cognitive Revolution information-processin
  g psychology replaced behaviorism
• Cognitive science brings together theories and
  experimental evidence to model internal
  activities of the brain

23
Thinking Humanly Cognitive Science

• Cognitive science and modeling the activities of
  the brain
• What level of abstraction? Knowledge or
  Circuits?
• How to validate models?
• Top-down Predicting and testing behavior of
  human subjects
• Bottom-up Direct identification from
  neurological data
• Simulation Building computer/machine simulated
  models and reproduce results

24
Thinking Rationally Laws of Thought

• Aristotle ( 450 B.C.) attempted to codify right
  thinking
• What are correct arguments/thought processes?
• Example
• Socrates is a man, all men are mortal therefore
  Socrates is mortal
• Several Greek schools developed various forms of
  logic
• notation plus rules of derivation for thoughts.

25
Thinking Rationally Laws of Thought

• Problems
• Uncertainty Not all facts are certain
• the flight might be delayed
• Resource limitations
• Not enough time to compute/process
• Not enough accuracy
• Etc.

26
Acting Rationally The Rational Agent

• Rational behavior Doing the right thing!
• Right thing maximize the expected return
• Provides the most general view of AI because it
  includes
• Correct inference (Laws of thought)
• Uncertainty handling
• Resource limitation considerations (e.g., reflex
  vs. deliberation)
• Cognitive skills (NLP, knowledge representation,
  ML, etc.)

27
Acting Rationally The Rational Agent

• Advantages
• More general
• Its goal of rationality is well defined

28
How to achieve AI?

• How is AI research done?
• Theoretical
• Experimental
• Basic
• applied
• There are two main lines of research
• Biological, study humans and imitate their
  psychology or physiology.
• phenomenal, study and formalize common sense
  facts about the world.

29
How to achieve AI?

• There are two main lines of research
• Biological, study humans and imitate their
  psychology or physiology.
• phenomenal, study and formalize common sense
  facts about the world and the problems that the
  world presents to the achievement of goals.
• The two approaches interact to some extent, and
  both should eventually succeed. It is a race, but
  both racers seem to be walking. John McCarthy

30
Branches of AI

• Logical AI
• Search
• Natural language processing
• pattern recognition
• Knowledge representation
• Inference From some facts, others can be
  inferred.
• Automated reasoning
• Learning from experience
• Planning To generate a strategy for achieving
  some goal

31
AI Prehistory
32
Brief History of AI
Next time implement links
Thinking RationallyLaws of Thought
33
Roots of AI in Science

• Aristotle(b.384-) syllogism formal reasoning
• Ramon Lull (b.1235) Ars Magna a machine
  capable of answering all questions
• Rene Descartes (1596) mind / body separation
  (dualism) "cogito ergo sum
• Wilhelm Liebniz (1646-1716) a mechanical concept
  generator "materialism"
• Charles Babbage(1792-1871), Ada Lovelace
  (1815-1860) Analytical Engine a
  general-purpose calculator
• George Boole(1815-1864) logic algebras - logical
  encoding and calculation of thoughts
• Gottlob Frege(1848-1925) predicate calculus

34
Birth of Artificial Intelligence
35
The Beginning of AI

• McCulloch Pitts
• developed theory of artificial neurons (precursor
  to ANN's) 1943
• Alan Turing "Can Machines Think?"
• the turing test (1950)
• the turing machine
• Marvin Minsky Dean Edmonds
• first ANN constructed, 1951
• John McCarthy
• convened the Dartmouth conference that coined the
  term artificial intelligence (AI) (1956) and set
  the research agenda
• symbolic AI
• connectionism
• LISP (list processing) 1958 1st AI language

36
The Rise of AI
37
An Optimistic Start

• In the 50's, 60's and early 70's, much exciting
  progress was being made in AI
• Chess
• Claude Shannon, 1950
• The Logic Theorist
• Alan Newell, Cliff Shaw, Herb Simon, 1957
• Checkers (Machine Learning)
• Arthur Samuels, 1959
• Eliza - NLP
• Joseph Weizenbaum, 1966
• DENDRAL Knowledge-Based System
• Feigenbaum, Buchanan, Lederberg, 1969
• SHRDLU NLP (Blocks World)
• Terry Winnograd, 1972
• GPS (General Problem Solver)
• Alan Newell Herb Simon, 1972

38
The 70s

• Birth and Rise of Expert Systems

39
The Plateau

• In the 70's, AI researchers began to discover
  that the problem wasn't as easy as it looked!
• The Frame Problem
• Lack of Common Sense Reasoning
• Combinatorial Explosion
• The Gap "Toy" vs. "Real" worlds
• Perceptrons, by Minsky Papert (1969) proved
  limitations of perceptron networks and acted to
  limit significant research in the 70's
• Lighthill Report 1973 curtailed research
  funding in British Universities
• AI developed a reputation as "over-hyped" and
  unrealistic

40
The 80s
Commercialization of Expert Systems Rebirth of
Artificial Neural Networks
41
Commercial Success

• Despite it's reputation as "over-hyped", certain
  AI applications became very successful during the
  70's 80's
• Expert Systems
• Industrial Robotics
• Planning Scheduling Applications
• AI became a 2,000,000,000 industry by 1988

42
Nowadays
43
The Gartner Hype Curve

• Interest in AI followed this pattern, typical of
  the hype surrounding new technologies

44
AI State of the art

• Have the following been achieved by AI?
• World-class chess playing
• Playing table tennis
• Cross-country driving
• Solving mathematical problems
• Discover and prove mathematical theories
• Engage in a meaningful conversation
• Understand spoken language
• Observe and understand human emotions

45
Types of expertise (with examples)
46
Types of expertise (with examples)
47
Types of expertise (with examples)
48
Types of expertise (with examples)
49
Types of expertise (with examples)
50
Types of expertise (with examples)
51
A driving example Grand Challenge

• Goal

52
Artificial Intelligence Applications
53
AI Application Areas in Business
54
Components of Expert Systems
55
Expert System Applications
56
Outlook

• AI is a very exciting area right now.
• This course will teach you the foundations.
• In addition, we will use the Beobot example to
  reflect on how this foundation could be put to
  work in a large-scale, real system.