Learning Center
Plans & pricing Sign in
Sign Out



									CSE 471/598

Introduction to
Artificial Intelligence

                                                    Spring 2004
  TA: Srihari Venkatesan, Brickyard ?
  TBA soon,, and

               CSE 471/598, H. Liu       2
The course
 What is AI (many definitions of AI)
    One definition: a field to enable
     computers with human-level intelligence
     with attempts to understand intelligent
 What is this course about
    understand ourselves better
    build automated intelligent agents
    improve problem solving skills
                   CSE 471/598, H. Liu         3
The course (2)
    Projects (30%, 2*15%) – all in Lisp
    Exam(s) (2*25%)
    Homework (~20%)
    Quizzes and class participation (~10%)
    Late penalty, YES.
    Academic integrity

                         CSE 471/598, H. Liu             4
  Text Book: AI - A Modern Approach
  Reading assignment: chapters covered
  15 weeks - about 13-15 chapters
  One major subject per week

                                    Try to keep up and
                                      avoid catch-up

              CSE 471/598, H. Liu                    5
Plan (2)
  Major topics
     Intelligent agents
     Problem solving
     Knowledge and reasoning
     Acting logically                        TIP
     Learning                          Comprehend the topics
                                        with your common sense
     Uncertainty

                  CSE 471/598, H. Liu                            6
Welcome to this class!

  We will work together throughout
  this semester.
  Questions and suggestions are most

               CSE 471/598, H. Liu     7
Introduction of AI and LISP
- Gearing up for a fun semester
about intelligent agents
What is AI (2)
  Acting humanly: The Turing test (1950)
     What do we need to pass the test
  Thinking humanly: Cognitive modeling
     “Think-aloud” to learn from human and
      recreate in computer programs (GPS)
  Thinking rationally: Syllogisms, Logic
  Acting rationally: A rational agent

                  CSE 471/598, H. Liu         9
Foundations of AI
  Philosophy (428 B.C. - Present) –
  reasoning and learning
     Can formal rules be used to draw valid
     How does the mental imind arise from a
      physical brain?
     Where does knowledge come from?
     How does knowledge lead to action?

                    CSE 471/598, H. Liu        10
Mathematics (c. 800 - Present) - logic, probability,
decision making, computation
   What are the formal rules to draw conclusions?
   What can be computed?
   How do we reason with uncertain information?
Economics (1776-present)
   How should we make decisions so as to maximize
   How should we do this when others may not go along?
   How should we do this when the payoff may be far in
    the future?

                    CSE 471/598, H. Liu              11
Neuroscience (1861-present)
   How do brains process information
Psychology (1879 - Present) -
investigating human mind
   How do humans and animals think and act?
Computer engineering (1940 - Present) -
ever improving tools
   How can we build an efficient computer?

                  CSE 471/598, H. Liu          12
Control theory and Cybernetics (1948-
   How can artifacts operate under their own
Linguistics (1957 - Present) - the structure
and meaning of language
   How does language relate to thought?

                   CSE 471/598, H. Liu          13
Brief History of AI
  Gestation of AI (1943 -1955)
     McCulloch and Pitts’s model of artificial neurons
     Minsky’s 40-neuron network
  Birth of AI (1956)
     A 2-month Dartmouth workshop of 10 attendees –
      the name of AI
     Newell and Simon’ Logic Theorist
  Early enthusiasm, great expectations (1952 -
     GPS by Newell and Simon, Lisp by McCarthy, Blockworld
      by Minsky

                        CSE 471/598, H. Liu               14
AI facing reality (1966 - 1973)
   Many predictions of AI coming successes
      A computer would be a chess champion in 10 years (1957)
   Machine translation – Syntax is not enough
   Intractability of the problems attempted by AI
Knowledge-based systems (1969 - 1979)
   Knowledge is power, acquiring knowledge from experts
   Expert systems (MYCIN)
AI - an industry (1980 - present)
   Many AI systems help companies to save money and
    increase productivity

                     CSE 471/598, H. Liu                  15
The return of neural networks (1986 – present)
   PDP books by Rumelhart and McClelland
   Connectionist models vs. symbolic models
AI – a science (1987 – present)
   Build on existing theories vs. propose brand new ones
   Rigorous empirical experiments
   Learn from data – data mining
AI – intelligent agents (1995 – present)
   Working agents embedded in real environments
    with continuous sensory inputs

                     CSE 471/598, H. Liu                16
Some examples of AI
  Smart bombs                       Biometrics
  Deep Blue, and others             Communications
  E-Game industry                   (email, word
  Intelligent houses                processor)
  Intelligent appliances            Auto driving from E to
                                    W (98% vs. 2%)
                                    Consumer protection

                   CSE 471/598, H. Liu                  17
Refresher for LISP
  What is it?
     ANSI Common Lisp, Paul Graham, Prentice
  Input (e.g., terminal, files)
  Output (e.g., files, printing)
  Processing (various operations)
  How to run it?

                   CSE 471/598, H. Liu          18

To top