Bài giảng Trí tuệ nhân tạo - Chapter 1: Introduction
Introduction
• What is AI?
• The foundations of AI
• A brief history of AI
• The state of the art
• Introductory problems
Cao Hoang Tru
CSE Faculty - HCMUT
1
13 February, 2009
What is AI?
Cao Hoang Tru
CSE Faculty - HCMUT
2
13 February, 2009
What is AI?
• Intelligence: “ability to learn, understand and think”
(Oxford dictionary)
Cao Hoang Tru
CSE Faculty - HCMUT
3
13 February, 2009
What is AI?
Thinking humanly
Thinking rationally
Acting rationally
Acting humanly
Cao Hoang Tru
CSE Faculty - HCMUT
4
13 February, 2009
Acting Humanly: The Turing Test
• Alan Mathison Turing (1912-1954)
Cao Hoang Tru
CSE Faculty - HCMUT
5
13 February, 2009
Turing Award
• A.M. Turing Award
ACM's most prestigious technical award is accompanied by a
prize of $250,000. It is given to an individual selected for
contributions of a technical nature made to the computing
community. The contributions should be of lasting and major
technical importance to the computer field. Financial support of
the Turing Award is provided by the Intel Corporation and
Google Inc.
Cao Hoang Tru
CSE Faculty - HCMUT
6
13 February, 2009
Turing Award
2007 Clarke, Edmund M
2007 Emerson, E Allen
2007 Sifakis, Joseph
2000 Yao, Andrew Chi-Chih 1988 Sutherland, Ivan
1977 Backus, John
1999 Brooks, Frederick P.
1998 Gray, Jim
1987 Cocke, John
1976 Rabin, Michael O.
1976 Scott, Dana S
2006 Allen, Frances E
2005 Naur, Peter
1986 Hopcroft, John E
1986 Tarjan, Robert E
1975 Newell, Allen
1975 Simon, Herbert A.
1997 Engelbart, Douglas
1996 Pnueli, Amir
1985 Karp, Richard M
1984 Wirth, Niklaus E
2004 Cerf, Vinton
2004 Kahn, Robert E
1974 Knuth, Donald E.
1973 Bachman, Charles W.
1972 Dijkstra, E. W.
1995 Blum, Manuel
2003 Kay, Alan
1983 Ritchie, Dennis M.
1983 Thompson, Kenneth Lane
1994 Feigenbaum, Edward
199 Reddy, Raj
2002 Adleman, Leonard M.
2002 Rivest, Ronald L.
2002 Shamir, Adi
1971 McCarthy, John
1970 Wilkinson, J. H.
1969 Minsky, Marvin
1968 Hamming, Richard
1967 Wilkes, Maurice V.
1966 Perlis, A. J.
1982 Cook, Stephen A
1981 Codd, Edgar F.
1993 Hartmanis, Juris
1993 Stearns, Richard E
2001 Dahl, Ole-Johan
2001 Nygaard, Kristen
1992 Lampson, Butler W.
1991 Milner, A J
1980 Hoare, C. Antony R.
1979 Iverson, Kenneth E.
1978 Floyd, Robert W
1990 Corbato, Fernando J.
1989 Kahan, William
Cao Hoang Tru
CSE Faculty - HCMUT
7
13 February, 2009
Acting Humanly: The Turing Test
• “Computing Machinery and Intelligence” (1950)
Cao Hoang Tru
CSE Faculty - HCMUT
8
13 February, 2009
Acting Humanly: The Turing Test
Imitation Game
Human
Human Interrogator
AI System
Cao Hoang Tru
CSE Faculty - HCMUT
9
13 February, 2009
Acting Humanly: The Turing Test
• 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.
Cao Hoang Tru
CSE Faculty - HCMUT
10
13 February, 2009
Thinking Humanly: Cognitive Modelling
• Not content to have a program correctly solving a
problem.
More concerned with comparing its reasoning steps
to traces of human solving the same problem.
• Requires testable theories of the workings of the
human mind: cognitive science.
Cao Hoang Tru
CSE Faculty - HCMUT
11
13 February, 2009
Thinking Rationally: Laws of Thought
• Aristotle was one of the first to attempt to codify “right
thinking”, i.e., irrefutable reasoning processes.
• Formal logic provides a precise notation and rules for
representing and reasoning with all kinds of things in
the world.
• Obstacles:
− Representation of informal knowledge.
− Computational complexity and resources.
Cao Hoang Tru
CSE Faculty - HCMUT
12
13 February, 2009
Acting Rationally
• Acting so as to achieve one’s goals, given one’s
beliefs.
• Does not necessarily involve thinking.
• Advantages:
− More general than the “laws of thought” approach.
− More amenable to scientific development than human-
based approaches.
Cao Hoang Tru
CSE Faculty - HCMUT
13
13 February, 2009
The Foundations of AI
• Philosophy (423 BC
−
present):
− Logic, methods of reasoning.
− Mind as a physical system.
− Foundations of learning, language, and rationality.
• Mathematics (c.800
−
present):
− Formal representation and proof.
− Algorithms, computation, decidability, tractability.
− Probability.
Cao Hoang Tru
CSE Faculty - HCMUT
14
13 February, 2009
The Foundations of AI
• Psychology (1879
− Adaptation.
−
present):
− Phenomena of perception and motor control.
− Experimental techniques.
• Linguistics (1957
−
present):
− Knowledge representation.
− Grammar.
Cao Hoang Tru
CSE Faculty - HCMUT
15
13 February, 2009
A Brief History of AI
• The gestation of AI (1943
−
1956):
− 1943: McCulloch & Pitts: Boolean circuit model of brain.
− 1950: Turing’s “Computing Machinery and Intelligence”.
− 1956: McCarthy’s name “Artificial Intelligence” adopted.
• Early enthusiasm, great expectations (1952
−
1969):
− Early successful AI programs: Samuel’s checkers,
Newell & Simon’s Logic Theorist, Gelernter’s Geometry
Theorem Prover.
− Robinson’s complete algorithm for logical reasoning.
Cao Hoang Tru
CSE Faculty - HCMUT
16
13 February, 2009
A Brief History of AI
• A dose of reality (1966
−
1974):
− AI discovered computational complexity.
− Neural network research almost disappeared after
Minsky & Papert’s book in 1969.
• Knowledge-based systems (1969
−
1979):
− 1969: DENDRAL by Buchanan et al..
− 1976: MYCIN by Shortliffle.
− 1979: PROSPECTOR by Duda et al..
Cao Hoang Tru
CSE Faculty - HCMUT
17
13 February, 2009
A Brief History of AI
• AI becomes an industry (1980
−
1988):
− Expert systems industry booms.
− 1981: Japan’s 10-year Fifth Generation project.
• The return of NNs and novel AI (1986
−
present):
− Mid 80’s: Back-propagation learning algorithm reinvented.
− Expert systems industry busts.
− 1988: Resurgence of probability.
− 1988: Novel AI (ALife, GAs, Soft Computing, …).
− 1995: Agents everywhere.
− 2003: Human-level AI back on the agenda.
Cao Hoang Tru
CSE Faculty - HCMUT
18
13 February, 2009
The State of the Art
• Computer beats human in a chess game.
• Computer-human conversation using speech
recognition.
• Expert system controls a spacecraft.
• Robot can walk on stairs and hold a cup of water.
• Language translation for webpages.
• Home appliances use fuzzy logic.
• ......
Cao Hoang Tru
CSE Faculty - HCMUT
19
13 February, 2009
Introductory Problem: Tic-Tac-Toe
X X
o
Cao Hoang Tru
CSE Faculty - HCMUT
20
13 February, 2009
Tải về để xem bản đầy đủ
38 trang
19120
Free
Bạn đang xem 20 trang mẫu của tài liệu "Bài giảng Trí tuệ nhân tạo - Chapter 1: Introduction", để tải tài liệu gốc về máy hãy click vào nút Download ở trên
File đính kèm:
- bai_giang_tri_tue_nhan_tao_chapter_1_introduction.pdf
