Kuliah 01 - Departemen Ilmu Komputer IPB

12/1/2009
Kontrak Perkuliahan
Yeni Herdiyeni
Departemen Ilmu Komputer FMIPA IPB
http://www.ilkom.fmipa.ipb.ac.id/~yeni
KECERDASAN BUATAN
•
•
•
•
•
Nama Mata Kuliah
Kode Mata Kuliah
Beban Kredit
Semester
Pengajar
: Kecerdasan Buatan
: KOM321
: 3(3-0)
: Gasal, 2009/2010
:
– Yeni Herdiyeni, S.Si. M.Komp (YHY)
– Mushtofa, S.Komp., MSc. (MUS)
KULIAH 01 - PENDAHULUAN
Deskripsi
• Pembahasan dalam matakuliah ini dimulai
dengan posisi dan ruang lingkup artificial
intelligent. Dilanjutkan dengan domain
permasalahan, berbagai metode searching,
berbagai representasi pengetahuan, matching,
metode inferensi (secara statistik, bayes, maupun
fuzzy), dan diakhiri dengan pembahasan
mengenai soft computing dengan tiga topik
utama yaitu : neural network, fuzzy system, dan
algoritma genetika.
Referensi
• Russell S. & Peter N. 2003.
Artificial Intelligence: A
Modern Approach. Edisi ke2. Prentice-Hall, New Jersey.
Tujuan
• Mahasiswa mampu menjelaskan sistem
kecerdasasan buatan serta mampu
merepresentasikan pengetahuan dan
menjelaskan metode inferensia pengambilan
kesimpulan
Kriteria Penilaian
• Nilai akhir (NA) adalah nilai kumulatif dari nilai ujian tengah
semester (UTS), ujian akhir semester (UAS), tugas
perorangan (TP), dan tugas kelompok atau proyek akhir
(PA). Metode dan bobot nilai sebagai berikut:
• UTS (1‐6) dan UAS (7‐14) dilakukan melalui ujian tertulis
dengan bobot masing‐masing 35%. Kisi‐kisi ujian akan
disampaikan pada pertemuan ke‐6 untuk UTS, dan pada
pertemuan ke‐14 untuk UAS.
• Nilai TP adalah rata‐rata dari semua tugas yang diberikan,
dan diberi bobot 10%
• Nilai PA terdiri dari nilai produk proyek (program komputer,
laporan) dan presentasi. Bobot nilai PA adalah 20%.
1
12/1/2009
Topik
Apakah Kecerdasan Buatan itu?
1.
2.
3.
4.
5.
6.
7.
8.
Kuliah 01 - Pendahuluan
Kuliah 02 - Penelusuran
Kuliah 03 & 04 : Teknik Penelusuran
Kuliah 05 & 06 :Agen berbasis logika preposisi
Kuliah 07 - Studi Kasus
Kuliah 08 & 09 : Agen berbasis logika predikat orde satu (FOL)
Kuliah 10 : Reasoning : Statistical Reasoning I (Probabilitas Bayes)
Kuliah 11 & 12 : Reasoning : Statistical Reasoning II (Bayesian
Networks)
9. Kuliah 13 :Machine Learning :
10. Kuliah 14 : Studi Kasus
How do we
emulate the
human brain?
How does
the human
brain work?
How do we
create
intelligence?
What is
intelligence?
Who cares? Let’s
do some cool and
useful stuff!
Why study AI?
How do we classify research as AI?
Does it emulate
the brain?
Does it
investigate
the brain?
Is it
intelligent?
Does it
investigate
intelligence?
If we don’t know how
it works, then it’s AI.
When we find out
how it works, it’s not
AI anymore…
Search engines
Science
Medicine/
Diagnosis
Labor
Appliances
Honda Humanoid Robot
What else?
Sony AIBO
Walk
Turn
http://world.honda.com/robot/
Stairs
http://www.aibo.com
2
12/1/2009
Natural Language Question
Answering
What is AI?
• Various definitions:
– Building intelligent entities.
– Getting computers to do tasks which require human intelligence.
• But what is “intelligence”?
• Simple things turn out to be the hardest to automate:
– Recognising a face.
– Navigating a busy street.
– Understanding what someone says.
• All tasks require reasoning on knowledge.
http://aimovie.warnerbros.com http://www.ai.mit.edu/projects/infolab/
Why do AI?
Who does AI?
• Two main goals of AI:
• Many disciplines contribute to goal of
creating/modelling intelligent entities:
– To understand human intelligence better. We
test theories of human intelligence by writing
programs which emulate it.
– To create useful “smart” programs able to do
tasks that would normally require a human
expert.
– Computer Science
– Psychology (human reasoning)
– Philosophy (nature of belief, rationality, etc)
– Linguistics (structure and meaning of language)
– Human Biology (how brain works)
• Subject draws on ideas from each
discipline.
Definisi Kecerdasan Buatan
The exciting new effort to
make computers thinks …
machine with minds, in the full
and literal sense”
(Haugeland 1985)
“The study of mental faculties
through the use of computational
models”
(Charniak et al. 1985)
“The art of creating machines
that perform functions that
require intelligence when
performed by people”
(Kurzweil, 1990)
A field of study that seeks to
explain and emulate intelligent
behavior in terms of
computational processes”
(Schalkol, 1990)
Systems that think like humans
Systems that think rationally
Systems that act like humans
Systems that act rationally
Approaches to AI
•
•
•
•
•
•
Searching
Learning
From Natural to Artificial Systems
Knowledge Representation and Reasoning
Expert Systems and Planning
Communication, Perception, Action
3
12/1/2009
Search
• “All AI is search”
– Game theory
– Problem spaces
• Every problem is a feature space of all possible
(successful or unsuccessful) solutions.
• The trick is to find an efficient search strategy.
Learning
• Explanation
– Discovery
– Data Mining
• No Explanation
– Neural Nets
– Case Based Reasoning
AI with Neural networks
Learning: Explanation
• Cases to rules
• Introduction to
perceptrons, Hopfield
networks, self-organizing
feature maps. How to size a
network? What can neural
networks achieve?
x 1(t)
w1
x 2(t)

w2
w
xn(t)
Approaches to AI
•
•
•
•
•
•
axon
y(t+1)
n
Genetic Algorithms.
Evolving Intelligent Systems
Searching
Learning
From Natural to Artificial Systems
Knowledge Representation and Reasoning
Expert Systems and Planning
Communication, Perception, Action
Introduction
to genetic algorithms
and their use in
optimization
problems.
4
12/1/2009
Approaches to AI
•
•
•
•
•
•
Rule-Based Systems
• Logic Languages
– Prolog, Lisp
• Knowledge bases
• Inference engines
Searching
Learning
From Natural to Artificial Systems
Knowledge Representation and Reasoning
Expert Systems and Planning
Communication, Perception, Action
Rule-Based Languages: Prolog
Father(abraham, isaac).
Father(haran, lot).
Father(haran, milcah).
Father(haran, yiscah).
Male(isaac).
Male(lot).
Female(milcah).
Female(yiscah).
Son(X,Y)  Father(Y,X), Male(X).
Daughter(X,Y)  Father(Y,X), Female(X).
Son(lot, haran)?
Ability-Based Areas
•
•
•
•
•
•
Computer vision
Natural language recognition
Natural language generation
Speech recognition
Speech generation
Robotics
Natural Language: Translation
“The flesh is weak, but the spirit is
strong”
 Translate to Russian
 Translate back to English
“The food was lousy, but the vodka was
great!”
5
12/1/2009
Natural Language Recognition
OBJ
Semantics
PERSON:
Joe
GOLD: X
TRANSACTION
REPT
AGNT
PERSON:
Fred
Context
sentence
w
VP
VP
NP
Syntax
Words
VP
NP
pronoun
n
verb
pronoun
d
You
give
me
NP
article
noun
the
gold
Audio
6