Artificial Intelligence - PowerPoint PPT Presentation

1 / 43
About This Presentation
Title:

Artificial Intelligence

Description:

Artificial Intelligence – PowerPoint PPT presentation

Number of Views:24
Avg rating:3.0/5.0
Slides: 44
Provided by: ensc7
Category:

less

Transcript and Presenter's Notes

Title: Artificial Intelligence


1
Artificial Intelligence
  • October 27, 2008

2
Cannibals and Missionaries
CCCMMM
3
(No Transcript)
4
Aristotle, 384-322 BC
  • Developed a set of formal procedures
  • -- the syllogism --
  • to capture the essence of rational thought
  • All cats are mammals
  • Some cats have no tails
  • Some mammals have no tails

5
The Brazen Head
6
The Characteristica Universalis of Leibniz
"It is obvious that if we could find characters
or signs suited for expressing all our thoughts
as clearly and as exactly as arithmetic expresses
numbers or geometry expresses lines, we could do
in all matters insofar as they are subject to
reasoning all that we can do in arithmetic and
geometry. For all investigations which depend on
reasoning would be carried out by transposing
these characters and by a species of calculus."
(Preface to the General Science, 1677.
7
Leibnizs Stepped Reckoner
8
(No Transcript)
9
1834 Charles Babbage invents the Analytical
Engine, programmed with punched cards
10
1842 Ada Lovelace writes the first computer
program. (To calculate the Bernoulli numbers)
11
Samuel Butler, Erewhon, 1871
  • there is no a priori improbability in the
    descent of conscious (and more than conscious)
    machines from those which now exist,
  • Erewhons The Book of the Machines

12
  • The present machines are to the future as the
    early Saurians to man. The largest of them will
    probably greatly diminish in size. Some of the
    lowest vertebrates attained a much greater bulk
    than has descended to their more highly organised
    living representatives, and in like manner a
    diminution in the size of machines has often
    attended their development and progress.
  • Erewhons The Book of the Machines

13
  • I fear the extraordinary rapidity with which
    they are becoming something very different to
    what they are at present. No class of beings have
    in any time past made so rapid a movement
    forward. Should not that movement be jealously
    watched, and checked while we can still check it?
    And is it not necessary for this end to destroy
    the more advanced of the machines which are in
    use at present..?
  • Erewhons The Book of the Machines

14
Can a Computer Think?
15
Can a Submarine Swim?
16
(No Transcript)
17
(No Transcript)
18
(No Transcript)
19
(No Transcript)
20
The ELIZA Effect
Joseph Weizenbaum, MIT, 1966
Patient I went for a long boat ride
Therapist Tell me about boats.
21
AI in the 40s, 50s and 60s
  • Games and Puzzles
  • Arthur Samuel, Checker-playing program,
  • 1947-1967

2. C.E. Shannon, Programming a Computer For
Playing Chess, Philosophy Magazine, Vol. 41, pp.
256-275 (1960)
22
1992 Chinook plays Tinsley
23
1994 Chinook plays Lafferty
24
(No Transcript)
25
(No Transcript)
26
AI in the 40s, 50s and 60s
  • Games and Puzzles

3. Newell, Shaw and Simon, General
Problem Solver, 1963 (abandoned 1967).
4. John McCarthy, LISP
5. Rosenblatt, Perceptrons
27
Newell and Simon with some general problems
28
LISP
(defun factorial(n) (cond(( n 0) 1)
t ( n (factorial(- n 1))))))
29
(No Transcript)
30
(No Transcript)
31


?1
?6

?2


?5
?3

?4
32
?1

?2

?3

?
Concave
?4

?5

?6

33
(No Transcript)
34
AI in the Seventies and Eighties
  • A belated realization in most situations,
    intelligent behaviour requires knowledge

35
AI in the Seventies and Eighties
  • Minsky, Frames
  • Winograd, SHRDLU
  • Rumelhart and McClellan, Parallel Distributed
    Programming (return of the Perceptron)
  • Expert Systems

36
(No Transcript)
37
(No Transcript)
38
(No Transcript)
39
(No Transcript)
40
(No Transcript)
41
Rumelhart and McClellandParallel Distributed
Processing
  • Representing knowledge by the strengths of
    associations between different concepts, rather
    than as lists of facts, yields programs that can
    learn from example.

42
(No Transcript)
43
Expert Systems(rule-based)
  • Represent knowledge as a number of ifthen
    rules plus an inference engine.

E.g, IF temperature is high AND rash is
present, THEN patient has measles.
Write a Comment
User Comments (0)
About PowerShow.com