Professional Documents
Culture Documents
Contact Me
ARTIFICIAL
INTELLIGENCE
Introduction &
Review at Glance
What is AI?
Views of AI fall into four categories:
Thinking humanly
Acting humanly
Thinking rationally
Acting rationally
intelligently?"
Operational test for intelligent behavior: the Imitation Game
years
Suggested major components of AI: knowledge, reasoning,
language understanding, learning
psychology
Requires scientific theories of internal activities of the
brain
-- How to validate? Requires
1) Predicting and testing behavior of human subjects
(top-down)
or 2) Direct identification from neurological data
(bottom-up)
Both approaches (roughly, Cognitive Science and
Cognitive Neuroscience)
are now distinct from AI
Rational agents
An agent is an entity that perceives and acts
This course is about designing rational agents
Abstractly, an agent is a function from percept
histories to actions:
[f: P* A]
For any given class of environments and tasks, we
seek the agent (or class of agents) with the best
performance
Caveat: computational limitations make perfect
rationality unachievable
design best program for given machine resources
AI prehistory
Philosophy
Abridged history of AI
1943
1950
1956
195269
1950s
1965
196673
196979
1980-1986-1987-1995--
Kasparov in 1997
Proved a mathematical conjecture (Robbins conjecture)
unsolved for decades
No hands across America (driving autonomously 98% of the
time from Pittsburgh to San Diego)
During the 1991 Gulf War, US forces deployed an AI logistics
planning and scheduling program that involved up to 50,000
vehicles, cargo, and people
NASA's on-board autonomous planning program controlled the
scheduling of operations for a spacecraft
Proverb solves crossword puzzles better than most humans
Tujuan AI
menciptakan komputer-komputer yang
Teknik-teknik AI
Teknik-teknik AI terutama digunakan untuk
Contoh teknik AI :
General Problem Solving
Fuzzy Logic
Neural Network
Neural Fuzzy
Genetic algorithm
Biologis
..
AI on Wall Street
Perhaps the biggest return on AI is potentially on Wall
Street. Substantial attention has been has been given to
the development of automated trading systems, integrating
AI into capital management, and using AI in capital
planning.
However, information about such systems is generally
limited, since disclosure of successful approaches could
lead to the loss of competitive advantage, and large sums
of money.
One activity that appears to be generating the greatest
interest on Wall Street is that of data mining, using
approaches such as neural networks.
Task Domains of
Artificial Intelligence
Searching
Searching:
Logika/Logika formal/predikat kalkulus
backtracking
Data:
Representasi Pengetahuan:
List/Graf
Database
C
C++
Aplikasi Artificial
Intelligence (AI)
A R T IF IC IA L IN T E L L IG E N C E
A p lik a i Ilm u
F a ls a f a h
S is te m P a k a r
S is te m
B e rb a s is
P e n g e ta h u a n
S is te m
B e la ja r
s is te m L o g ic
Fuzzy
A p lik a s i Ilm u
K o m p u te r
G en era si
K e lim a
K o m p u te r
P em ro se sa n
P a ra rel
P em ro se sa n
S im b o lik
J a rin g a n
N eu ra l
A p lik a s i R o b o tic s
P e rsep si
V is u a l
P e ra b a a n
D e c te rity
P e n g a n g k u ta n
N a v ig a s i
A p lik a s i B a h a s a
A la m i
P
B
P
P
P
B
e n g e rtia n
ahasa
id a to
engakuan
e n te rje m a h a n
ahasa
S u b s is te m P e n y im p a n a n
M em o ri
Jangka
P a n ja n g
S u b s is te m
P e ra sa
S u b s is te m P e m ro s e s a n In f o rm a s i
M a ta
T e lin g a
In d e ra
P e ra s a L a in
M em o ri
Jan gka
P endek
C on
d a
P enga
D a
to h
n
ku an
ta
H a s il R e s p o n
P e m b u a ta n
K e p u tu s a n
K e p u tu s a n
D ib u a t
P ro se s
P e n y e s u a ia n
T ugas
D ija la n k a n
P e m b a g ia n T u g a s
H a s il F is ik
DSS
Karakteristik
ES
Fungsi
Membuat keputusan
melebihi kemampuan
manajer
Alur Penalaran
Tidak terperinci
Kemampuan
memberikan alasan
Tidak ada
Ada, terbatas
Kemampuan
menjelaskan
Terbatas
Ada
Pengambil Keputusan
Sistem
Numerik
Simbolik