Transcript 2(수정)

robotics.stanford.edu/~latombe/cs121/2003/home.htm
Introduction to AI
Russell and Norvig:
Chapters 1 and 2
CS121 – Winter 2003
Found on the Web …
AI
is the reproduction of the methods of
Intelligent
behavior
human
reasoning or intuition
Computer
Using computational models
to simulate
intelligent (human) behavior and
processes
AI is the study of mental faculties
through the Humans
use computational methods
Introduction to AI
2
I personally think that AI started as a
rebellion against some form of establishment
telling us “Computers cannot perform certain
tasks requiring intelligence”
For example, for many years AI researchers
have regarded computational complexity
theory as irrelevant to their field.
They eventually had to reckon with it, but in
the meantime computational complexity had
also changed a lot.
Introduction to AI
3
What is AI?
Discipline that systematizes and automates
intellectual tasks to create machines that:
Act like humans
Act rationally
Think like humans
Think rationally
Introduction to AI
4
Act Like Humans
AI is the art of creating machines that
perform functions that require
intelligence when performed by humans
Methodology: Take an intellectual task
at which people are better and make a
computer do it •Prove a theorem
•Play chess
Turing test
•Plan a surgical operation
•Diagnose a disease
•Navigate
in
a
building
Introduction to AI
5
Chess
Name: Garry Kasparov
Title: World Chess
Champion
Crime: Valued greed
over common sense
Humans are still better at making up excuses.
© Jonathan Schaeffer
Introduction to AI
6
Perspective on Chess: Pro
“Saying Deep Blue doesn’t really think
about chess is like saying an airplane
doesn't really fly because it doesn't flap
its wings”
Drew McDermott
© Jonathan Schaeffer
Introduction to AI
7
나비가 나는 이유?
나비는 유체역학적으로 날 수가 없다. 그러나
나비는 그 사실을 모르기 때문에 날 수 있다.
나비는 유체역학적으로 날기에 부적합하다.
제비는 적합하다. 그러나 나비는 제비
못지않게 잘 번성하고 있다.



나비처럼 나는 것도 이유가 있다.
어떤 나비는 미국에서 호주까지 날아가기도 한다.
흉내보다는 같은 기능을 하면 충분!!
 두 발로 걷는 로봇 ? 지네 같은 로봇 ?
Introduction to AI
8
Perspective on Chess: Con
“Chess is the Drosophila of artificial
intelligence. However, computer chess has
developed much as genetics might have if the
geneticists had concentrated their efforts
starting in 1910 on breeding racing Drosophila.
We would have some science, but mainly we
would have very fast fruit flies.”
John McCarthy
© Jonathan Schaeffer
Introduction to AI
9
Think Like Humans
How the computer performs functions
does matter
Comparison of the traces of the
reasoning steps
Cognitive science  testable theories of
the workings of the human mind
But, do we want to duplicate human imperfections?
Introduction to AI
10
Think/Act Rationally
Always make the best decision given what is
available (knowledge, time, resources)
•Connection
to economics,
A performance
measure operational
is required research,
and
control theory
 객관적인가?
청소로봇, 보상(reward)
디자이너의
•But ignores
role평가기준?
of consciousness, emotions,
 자원의 제한이 있을 때?
fear
of dying on intelligence
Perfect knowledge, unlimited resources 
logical reasoning
Imperfect knowledge, limited resources 
(limited) rationality
Introduction to AI
11
Bits of History
1956: The name “Artificial Intelligence”
was coined. (Would “computational
rationality” have been better?)
Early period (50’s to late 60’s):
Basic principles and generality




General problem solving
Theorem proving
Games
Formal calculus
Introduction to AI
12
Bits of History
1969-1971: Shakey the
robot (Fikes, Hart, Nilsson)
Logic-based planning
(STRIPS)
Motion planning (visibility
graph)
Inductive learning (PLANEX)
Computer vision
Introduction to AI
13
Bits of History
Knowledge-is-Power period (late 60’s to
mid 80’s):


Focus on narrow tasks require expertise
Encoding of expertise in rule form:
If:
the car has off-highway tires and
4-wheel drive and
high ground clearance
Then: the car can traverse difficult terrain (0.8)



Knowledge engineering
5th generation computer project
CYC system (Lenat)
Introduction to AI
14
Bits of History
AI becomes an industry (80’s – present):





Expert systems: Digital Equipment,
Teknowledge, Intellicorp, Du Pont, oil
industry, …
Lisp machines: LMI, Symbolics, …
Constraint programming: ILOG
Robotics: Machine Intelligence Corporation,
Adept, GMF (Fanuc), ABB, …
Speech understanding
Introduction to AI
15
Bits of History
The return of neural networks, genetic
algorithms, and artificial life (80’s – 90’s)
Increased connection with economics,
operational research, and control theory
(90’s – present)
AI becomes less philosophical, more
technical and mathematically oriented
Introduction to AI
16
Predictions and Reality … (1/3)
In the 60’s, a famous AI professor from MIT
said: “At the end of the summer, we will have
developed an electronic eye”
As of 2002, there is still no general computer
vision system capable of understanding
complex dynamic scenes
But computer systems routinely perform road
traffic monitoring, facial recognition, some
medical image analysis, part inspection, etc…
Introduction to AI
17
Predictions and Reality … (2/3)
In 1958, Herbert Simon (CMU) predicted
that within 10 years a computer would
be Chess champion
This prediction became true in 1998
Today, computers have won over world
champions in several games, including
Checkers, Othello, and Chess, but still do
not do well in Go
Introduction to AI
18
Predictions and Reality … (3/3)
In the 70’s, many believed that computer-controlled
robots would soon be everywhere from manufacturing
plants to home
Today, some industries (automobile, electronics) are
highly robotized, but home robots are still a thing of
the future
But robots have rolled on Mars, others are performing
brain and heart surgery, and humanoid robots are
operational and available for rent (see:
http://world.honda.com/news/2001/c011112.html)
Introduction to AI
19
Mistakes …
Often, the potential of a new field is
over-estimated in its early age, but
under-estimated over the longer term
AI proponents have over-estimated the
need for smart software, and underestimated the feasibility and potential of
large software systems based on
massive coding effort
Introduction to AI
20
생물학적으로 본 인간
인류의 진화
뇌의 크기
언어의 사용
도구의 사용
직립보행
사회생활
예측에 의한 행동
?
Introduction to AI
21
인간과 다른 유인원
Introduction to AI
22
Sahelanthropus tchadensis
뇌의 진화과정
원인류
네안데르탈 인
Homo sapiens
1300-1700 cc
600만
500만
400만
300만
유럽인
100만
200만
아프리카인
오스트랄로 피테쿠스
뇌용적 :
400-500 cc
Homo habilus
(handy man)
600-800 cc
Homo erectus
동아시아인
800-1200 cc
호주 원주민
Introduction to AI
23
뇌의 용량
Introduction to AI
24
인류의 진화
Introduction to AI
25
Human Brain
Chimpanzee Brain
Introduction to AI
26
보복전쟁 원인은 진화덜된 두뇌탓
미국 폴 로스코 교수 주장
미국 과학진흥협회 (AAAS) annual meeting
“핵 기술을 보유한 인간의 두뇌가 여전히 석기 시대 수준에 머물러 있다”
“자신뿐 아니라 자기 종족까지 죽이는
‘복수’ 행위는
정상적인 진화의 산물이 아니다”
Introduction
to AI
27
일란성 쌍둥이 연구
건선
강한 유전자 영향
우울병
정신분열병
IQ
신경증
당뇨병
천식
심장병
암
다발성 경화증
Introduction to AI
약한 유전자 영향
28
언어의 진화
Introduction to AI
29
'Speech Gene' Tied to Modern Humans
FOXP2 gene
- first identified by Monaco’s group at Oxford University (Science 2001)
- 715 amino acids, two amino acid mutation in human lineage since 6 million years ago –
fixed at 120,000 – 200,000 years ago (Svante Paabo, Nature 2002)
Evolutionary leap. One of these primates is able to talk about what
he's seeing; the other isn't. Introduction to AI
30
언어를 관할하는 FOXP2 유전자의 돌연변이
Introduction to AI
31
유전자의 영향
IQ
(어머니와 아들)
모성애 (아버지와 딸 (NAST))
도파민 D4 수용체(11번 염색체)
• 3번 exon(long) : 창조성, 탐구성, 스릴 추구
• 3번 exon(short) : 완고, 융통성 결여
• D4 장애 : 정신분열병
Introduction to AI
32
아인슈타인의 뇌
Introduction to AI
33
폭력의 생물학
Richard J. Davidson et al., Science 2000
(폭력과 전전두엽 장애 – 세로토닌 신경계 장애)
연쇄살인자 – 세로토닌 장애 – 책임문제
Introduction to AI
정신분열병 – 도파민 장애 – 살인 - 면죄부
34
생체 전자 공학
기록전극 부분의 확대도
전극의 전체 레이아웃
배양을 시작한 직후의 신경세포종의 모습
배양 후 2일이 경과한 신경세포종의 모습
Introduction to AI
35
생체전자공학
뇌에 기계 또는 전자적 연결


눈 수술
귀 수술
Introduction to AI
36
뇌의 특정 유전자 과도 발현하는 형질 전환 마우스 제조
(smart mice)
T. V. P. BLISS et al., Nature,1999
transgenic mice overexpressing
the NR2B subunit of the NMDA
receptor
Introduction
to AI
37
최초의 유전자 치료술 (중증 복합 면역결핍증, SCID)
Introduction to AI
38
Mistakes …
Often, the potential of a new field is over-estimated
in its early age, but under-estimated over the longer
term
What about Bio-informatics?

줄기세포의 치료효과
 쥐의 실험에 의하면 척추장애를 완벽히 치료
 그러나 저항력이 없는 쥐에서는 바로 암으로 전이, 있을 때에도
3개월 뒤면 암으로 전이
? 탄소 큐브 (나노기술)
 완벽한 새로운 물질
 인류는 경험하지 못했으며, 가장 무서운 발암물질?
핵, 유전자변형???
Introduction to AI
39
Intelligent Agent
인간의 능력을 대신할 수 있는


부분적: 걷는? 말하는? 판단하는?
인간과 같은?
지능적 능력을 가진


인간과 다른 형태의?
말하는 개? 말하는 앵무새? 덧셈을 하는 개?
비교: SOAP, Service-oriented approach, XML,
Context, …
Introduction to AI
40
Notion of an Agent
sensors
?
environment
agent
actuators
laser range
finder
sonars
Introduction to AI
touch sensors
41
Notion of an Agent
sensors
?
environment
agent
actuators
Introduction to AI
42
Notion of an Agent
sensors
?
environment
agent
actuators
•Locality of sensors/actuators
•Imperfect modeling
•Time/resource constraints
•Sequential interaction
•Multi-agent
worlds
Introduction to AI
43
단순화한 인공지능 문제
에이전트의 조건




성공을 평가한 판단기준
환경 또는 응용영역에 대한 사전지식
Agent가 행할 수 있는 행위
현재까지 한 행위와 결과에 대한 인식
문제의 어려움






Fully observable vs. Partially observable
Deterministic vs. Stochastic
Episodic vs. Sequential
Static vs. Dynamic
Discrete vs. Continuous
Single agent vs. Multiagent
Introduction to AI
44
Example: Tracking a Target
• The robot must keep
the target in view
• The target’s trajectory
is not known in advance
• The robot may not know
all the obstacles in
advance
• Fast decision is required
robot
Introduction to AI
target
45
Syllabus
Representing
knowledge
Problem solving:


Search
Constraint satisfaction
Logic and Inference
Planning
Dealing with Uncertainty
Using knowledge


Acquiring knowledge

Adversarial search
Deciding under probabilistic
uncertainty
Belief networks
Inductive learning
Introduction to AI
46
Schedule
Prerequisite: CS103B or X
Basic algorithms, notions in
computational complexity
1/13 Search problems
1/15 Blind search
1/22 Heuristic search
1/27 Constraint
satisfaction
1/29 Constraint
propagation
2/3 Propositional Logic
2/5 Inference in PL
2/10 Planning
Basic logic
2/12 Uncertainty
2/19 Adversarial search
and game playing
2/24 Deciding under
probabilistic uncertainty
2/26 Belief networks
3/3 Learning decision trees
3/5 Version space and PAC
learning
3/10 Applications of AI to
motion planning
3/12 Conclusion
Introduction to AI
Basic probabilities
47
Web Site
robotics.stanford.edu/~latombe/cs121/2003/home.htm
Introduction to AI
48