Program Studi Teknik Informatika – UMM
PENGANTAR
KECERDASAN BUATAN
Program Studi Teknik Informatika – UMM
Setio Basuki, ST., MT.
Hal. 2
Penilaian
•
•
•
•
•
UTS
: 25%
UAS
: 30%
Tugas Besar : 20%
Tugas
: 15%
Kehadiran : 10%
10/31/2018
Hal. 3
Faculty Name:
Setio Basuki, ST., MT.
Research Interest:
Speech and Natural Language Processing
Machine Learning
Computational Social Science
Room:
4.18 - GKB III.
Contacts:
setio_basuki@umm.ac.id
setio.staf.umm.ac.id
10/31/2018
Hal. 4
Film/Produk/Talk
10/31/2018
Hal. 5
Cerdas dan Kecerdasan
http
://kbbi.web.id/
• cerdas/cer·das/ a 1 sempurna perkembangan akal
budinya (untuk berpikir, mengerti, dsb); tajam
pikiran: sekolah bertujuan mendidik anak agar menjadi
orang yg -- lagi baik budi;
• kecerdasan/ke·cer·das·an/ n 1 perihal
cerdas; 2 perbuatan mencerdaskan; kesempurnaan
perkembangan akal budi (spt kepandaian, ketajaman
pikiran): perpustakaan didirikan untuk meningkatkan ~
masyarakat;
10/31/2018
Hal. 6
Artifcial
(oxford dictionary)
Definition of artificial in English:
adjective
• Made or produced by human beings rather than occurring
naturally, especially as a copy of something natural:
▫ her skin glowed in the artificial light
▫ an artificial limb
▫ artificial flowers
10/31/2018
Hal. 7
Intelligence
(oxford dictionary)
Definition of intelligence in English:
noun
• The ability to acquire and apply knowledge and skills:
▫ an eminent man of great intelligence
• the ability to learn, understand and think in a logical way
about things; the ability to do this well.
10/31/2018
Hal. 8
10/31/2018
Hal. 9
Domain Kecerdasan Buatan
10/31/2018
Hal.
10
Domain Kecerdasan Buatan
10/31/2018
Hal.
11
Acting Humanly: Turing Test
• Merupakan pendekatan yang menyatakan bahwa
jika respon dari program komputer terhadap suatu
“natural conversation” tidak dapat dibedakan
dengan respon yang diperoleh dari manusia.
▫ Program komputer tersebut dapat dinyatakan sebagai
program yang cerdas.
• Dengan kata lain, kriteria Kecerdasan Buatan dapat
didekati oleh suatu program, yang mana program
tersebut dapat bertindak (memberikan respon)
layaknya seorang manusia.
▫ Turing Test merupakan salah satu test yang sering
diangkat sebagai contoh di dalam pemaparan aspek
ini.
10/31/2018
Hal.
12
Acting Humanly: Turing Test
• Pada 1950, Turing
menerbitkan “Computing
machinery and
intelligence”, dengan
mengajukan pertanyaan:
“Can machines think?”
• Pertanyaan tersebut
kemudian menjadi : “Can
machines behave
intelligently?”
10/31/2018
Hal.
13
Turing System: Alice
• Alice: the winner of several Loebner Prizes (2000,
2002, 2004), featured in NY Times and various
other media outlets.
• One judge out of 5 ranked it more believable than
one of the humans.
• About 30,000-40,000 canned phrases and
sentences, with a very elaborate rule base and
search engine for picking them.
10/31/2018
Hal.
14
Turing System: Julia
• Julia (1990-1995): Chatbot living in a Multi-User Dungeon (MUD)
• environment, expert in hockey
• MUDs have a rich but limited set of action verbs that users can
perform on each other; users can create content (rooms, objects
etc)
• Not quite natural language, but close
• Fooled at least one user into believing she was a real girl:
▫ barry says, ‘Hey girlfriend are you out there’
▫
▫
▫
▫
▫
▫
▫
10/31/2018
Julia says, ‘Hello, barry.’
barry says, ‘Hello, I love Your name. It’s sexy’
Julia says, ‘Me too, barry.’
barry says, ‘What are you doing there’
Julia says, ‘I’m just hanging around in The Hearts Room, barry.’
barry says, ‘Well come over to MY ROOM’
Julia says, ‘Could you say that again, it scrolled of my screen.’
Hal.
15
Turing System: Watson
• In February 2011, Watson (developed at IBM)
handily beat the two top human competitors in the
game of Jeopardy
• Watson computes probabilities of diferent answers,
based on evidence from the question, many
knowledge sources, and past questions
• It learns from feedback (success/failure) to adjust
how much it trusts diferent information sources
10/31/2018
Hal.
16
Turing System Requirement
•
•
•
•
•
•
Natural Language Processing
Knowledge Representation
Automated Reasoning
Machine Learning
Computer Vision
Robotics
10/31/2018
Hal.
17
Thinking Humanly: Cognitive Modelling
• Pendekatan ini berkaitan dengan suatu karakter
dari suatu program komputer yang dapat berfkir
seperti manusia, yang lebih tepatnya sering
dikaitkan dengan bagaimana suatu program
komputer dapat mensimulasikan/menjalankan
proses berpikir layaknya proses kognitif pada
manusia.
10/31/2018
Hal.
18
Thinking Humanly
• Studi tentang brain sebagai alat pemrosesan
informasi:
▫ Cognitive Science dan Neuroscience
10/31/2018
Hal.
19
Thinking Humanly
Cognitive Modelling
Computational Neuroscience
Sipp http://
www.artifcialbrains.com/blue-br
ain-project
10/31/2018
Hal.
20
Acting Rationally: Rational Agent
• Program komputer (Agent) yang dikembangkan
dapat “merasakan/melihat” keadaan lingkunganya
dan kemudian dapat menentukan serta melakukan
tindakan tertentu terhadap tujuan yang diinginkan
agent tersebut.
10/31/2018
Hal.
21
Acting Rationally: Rational Agent
10/31/2018
Hal.
22
Thingking Rationally: Law of Thought
• Yang dimaksud dengan Thinking Rationally adalah
pendekatan untuk memodelkan suatu knowledge
menggunakan suatu bentuk formal tertentu
(statement logika) untuk melaksanakan proses
reasoning di dalam suatu domain permasalahan
tertentu.
• Law of thought:
▫ “Right” / “Idealized” way of thinking
▫ Lojik: menghasilkan kesimpulan yang benar jika
disuplay oleh premis-premis yang benar, contoh:
Joko adalah pria. Semua pria adalah hidung belang. Joko
adalah pria hidung belang.
▫ Pendekatan lojik dari Kecerdasan Buatan
10/31/2018
Hal.
23
Aplikasi Kecerdasan Buatan
• Built based on a
Volkswagen car. An array
of sensors: cameras, laser
range fnders, radar, GPS
• Probabilistic reasoning and
machine learning
algorithms are the heart of
the software
• The robot is capable of
assessing how good the
data is, based on prior
training
10/31/2018
Hal.
24
Aplikasi Kecerdasan Buatan
• Deep Blue (IBM) defeats
world champion Gary
Kasparov in 1997
• Perception: advanced
features of the board
• Actions: choose a move
• Reasoning: heuristics to
evaluate board positions,
search
10/31/2018
Hal.
25
Aplikasi Kecerdasan Buatan
• Polaris (Univ. Alberta)
defends some of the best
on-line poker players in
2008
• Perception: features of the
game
• Action: choose a move
(card to play, bet, etc)
• Reasoning: search and
evaluation of possible
moves, probabilistic
reasoning, machine
learning
10/31/2018
Hal.
26
Aplikasi Kecerdasan Buatan
• Pathfnder (Heckerman,
1992): diagnosis of lymph
node disease.
• Perception: Symptom
patients, test result
• Reasoning: Bayesian
inference, machine
learning.
• Action: suggest tests,
make diagnosis.
10/31/2018
Hal.
27
Aplikasi Kecerdasan Buatan
• COBOT (Isbell et al, 2000): learning
chatbot in LambdaMOO
• Percepts: what users are present,
how experienced they are, how
much they interact with each other,
what they do with each other,
things being said...
• Actions: “verbs” that express
actions on others and on objects –
but restricted to a few
• E.g. proposing a conversation topic,
introducing two users to each other,
giving a piece of information
• Goals: maximize reward received
from other users
10/31/2018
Hal.
28
Aplikasi Kecerdasan Buatan
• Brain image analysis (T.
Mitchell, 2008)
• Perception: brain imaging
using fMRI technology
• Action: detect which word
(e.g. “hammer”,
“apartment”, ...) is read by
the person
• Reasoning: machine
learning
10/31/2018
Hal.
29
Aplikasi Kecerdasan Buatan
• ALVINN (D. Pomerleau, CMU,
1995): drives autonomously
on the highway at 55 mph,
for 21 miles
• Perception: digitized camera
image of the road
• Actions: 64 diferent steering
angles
• Reasoning: artifcial neural
network trained with Back
Propagation
10/31/2018
Hal.
30
Tugas Minggu 1
• “NONTON” Film atau Video dengan topik
Kecerdasan Buatan.
• Tugas Anda:
▫ Judul video/flm,
▫ Aktor utama/spaker,
▫ Deskripsi singkat kategori AI yang digunakan
(bisa lebih dari satu),
▫ Kelebihan/kekurangan, dan saran anda,
▫ Jelaskan teknologi sejenis (kalo sudah ada).
• Laporan ditulis perseorangan, pada kertas A4,
tulis tangan, rapi dan mudah dibaca.
• Pengumpulan: pertemuan selanjutnya!
10/31/2018
Hal.
31
Silabus
• Bagian I: Making Decisions
▫ Search & planning
▫ Knowledge Representation
• Bagian II: Reasoning under Uncertainty
▫ Bayes’ nets
▫ Fuzzy System
▫ Machine learning
• Overview: Applications
▫ Aplikasi dari Kecerdasan Buatan
10/31/2018
Hal.
32
Further Courses in AI
• Introduction to Neural Networks and Machine
Learning
• Machine Learning and Data Mining
• Pattern Recognition
• Uncertainty and Learning in Artifcial
Intelligence
• Image Understanding
• Computational Linguistics
• Knowledge Representation and Reasoning
• Computational Vision
10/31/2018
Hal.
33
-- End --
10/31/2018
KECERDASAN BUATAN
Program Studi Teknik Informatika – UMM
Setio Basuki, ST., MT.
Hal. 2
Penilaian
•
•
•
•
•
UTS
: 25%
UAS
: 30%
Tugas Besar : 20%
Tugas
: 15%
Kehadiran : 10%
10/31/2018
Hal. 3
Faculty Name:
Setio Basuki, ST., MT.
Research Interest:
Speech and Natural Language Processing
Machine Learning
Computational Social Science
Room:
4.18 - GKB III.
Contacts:
setio_basuki@umm.ac.id
setio.staf.umm.ac.id
10/31/2018
Hal. 4
Film/Produk/Talk
10/31/2018
Hal. 5
Cerdas dan Kecerdasan
http
://kbbi.web.id/
• cerdas/cer·das/ a 1 sempurna perkembangan akal
budinya (untuk berpikir, mengerti, dsb); tajam
pikiran: sekolah bertujuan mendidik anak agar menjadi
orang yg -- lagi baik budi;
• kecerdasan/ke·cer·das·an/ n 1 perihal
cerdas; 2 perbuatan mencerdaskan; kesempurnaan
perkembangan akal budi (spt kepandaian, ketajaman
pikiran): perpustakaan didirikan untuk meningkatkan ~
masyarakat;
10/31/2018
Hal. 6
Artifcial
(oxford dictionary)
Definition of artificial in English:
adjective
• Made or produced by human beings rather than occurring
naturally, especially as a copy of something natural:
▫ her skin glowed in the artificial light
▫ an artificial limb
▫ artificial flowers
10/31/2018
Hal. 7
Intelligence
(oxford dictionary)
Definition of intelligence in English:
noun
• The ability to acquire and apply knowledge and skills:
▫ an eminent man of great intelligence
• the ability to learn, understand and think in a logical way
about things; the ability to do this well.
10/31/2018
Hal. 8
10/31/2018
Hal. 9
Domain Kecerdasan Buatan
10/31/2018
Hal.
10
Domain Kecerdasan Buatan
10/31/2018
Hal.
11
Acting Humanly: Turing Test
• Merupakan pendekatan yang menyatakan bahwa
jika respon dari program komputer terhadap suatu
“natural conversation” tidak dapat dibedakan
dengan respon yang diperoleh dari manusia.
▫ Program komputer tersebut dapat dinyatakan sebagai
program yang cerdas.
• Dengan kata lain, kriteria Kecerdasan Buatan dapat
didekati oleh suatu program, yang mana program
tersebut dapat bertindak (memberikan respon)
layaknya seorang manusia.
▫ Turing Test merupakan salah satu test yang sering
diangkat sebagai contoh di dalam pemaparan aspek
ini.
10/31/2018
Hal.
12
Acting Humanly: Turing Test
• Pada 1950, Turing
menerbitkan “Computing
machinery and
intelligence”, dengan
mengajukan pertanyaan:
“Can machines think?”
• Pertanyaan tersebut
kemudian menjadi : “Can
machines behave
intelligently?”
10/31/2018
Hal.
13
Turing System: Alice
• Alice: the winner of several Loebner Prizes (2000,
2002, 2004), featured in NY Times and various
other media outlets.
• One judge out of 5 ranked it more believable than
one of the humans.
• About 30,000-40,000 canned phrases and
sentences, with a very elaborate rule base and
search engine for picking them.
10/31/2018
Hal.
14
Turing System: Julia
• Julia (1990-1995): Chatbot living in a Multi-User Dungeon (MUD)
• environment, expert in hockey
• MUDs have a rich but limited set of action verbs that users can
perform on each other; users can create content (rooms, objects
etc)
• Not quite natural language, but close
• Fooled at least one user into believing she was a real girl:
▫ barry says, ‘Hey girlfriend are you out there’
▫
▫
▫
▫
▫
▫
▫
10/31/2018
Julia says, ‘Hello, barry.’
barry says, ‘Hello, I love Your name. It’s sexy’
Julia says, ‘Me too, barry.’
barry says, ‘What are you doing there’
Julia says, ‘I’m just hanging around in The Hearts Room, barry.’
barry says, ‘Well come over to MY ROOM’
Julia says, ‘Could you say that again, it scrolled of my screen.’
Hal.
15
Turing System: Watson
• In February 2011, Watson (developed at IBM)
handily beat the two top human competitors in the
game of Jeopardy
• Watson computes probabilities of diferent answers,
based on evidence from the question, many
knowledge sources, and past questions
• It learns from feedback (success/failure) to adjust
how much it trusts diferent information sources
10/31/2018
Hal.
16
Turing System Requirement
•
•
•
•
•
•
Natural Language Processing
Knowledge Representation
Automated Reasoning
Machine Learning
Computer Vision
Robotics
10/31/2018
Hal.
17
Thinking Humanly: Cognitive Modelling
• Pendekatan ini berkaitan dengan suatu karakter
dari suatu program komputer yang dapat berfkir
seperti manusia, yang lebih tepatnya sering
dikaitkan dengan bagaimana suatu program
komputer dapat mensimulasikan/menjalankan
proses berpikir layaknya proses kognitif pada
manusia.
10/31/2018
Hal.
18
Thinking Humanly
• Studi tentang brain sebagai alat pemrosesan
informasi:
▫ Cognitive Science dan Neuroscience
10/31/2018
Hal.
19
Thinking Humanly
Cognitive Modelling
Computational Neuroscience
Sipp http://
www.artifcialbrains.com/blue-br
ain-project
10/31/2018
Hal.
20
Acting Rationally: Rational Agent
• Program komputer (Agent) yang dikembangkan
dapat “merasakan/melihat” keadaan lingkunganya
dan kemudian dapat menentukan serta melakukan
tindakan tertentu terhadap tujuan yang diinginkan
agent tersebut.
10/31/2018
Hal.
21
Acting Rationally: Rational Agent
10/31/2018
Hal.
22
Thingking Rationally: Law of Thought
• Yang dimaksud dengan Thinking Rationally adalah
pendekatan untuk memodelkan suatu knowledge
menggunakan suatu bentuk formal tertentu
(statement logika) untuk melaksanakan proses
reasoning di dalam suatu domain permasalahan
tertentu.
• Law of thought:
▫ “Right” / “Idealized” way of thinking
▫ Lojik: menghasilkan kesimpulan yang benar jika
disuplay oleh premis-premis yang benar, contoh:
Joko adalah pria. Semua pria adalah hidung belang. Joko
adalah pria hidung belang.
▫ Pendekatan lojik dari Kecerdasan Buatan
10/31/2018
Hal.
23
Aplikasi Kecerdasan Buatan
• Built based on a
Volkswagen car. An array
of sensors: cameras, laser
range fnders, radar, GPS
• Probabilistic reasoning and
machine learning
algorithms are the heart of
the software
• The robot is capable of
assessing how good the
data is, based on prior
training
10/31/2018
Hal.
24
Aplikasi Kecerdasan Buatan
• Deep Blue (IBM) defeats
world champion Gary
Kasparov in 1997
• Perception: advanced
features of the board
• Actions: choose a move
• Reasoning: heuristics to
evaluate board positions,
search
10/31/2018
Hal.
25
Aplikasi Kecerdasan Buatan
• Polaris (Univ. Alberta)
defends some of the best
on-line poker players in
2008
• Perception: features of the
game
• Action: choose a move
(card to play, bet, etc)
• Reasoning: search and
evaluation of possible
moves, probabilistic
reasoning, machine
learning
10/31/2018
Hal.
26
Aplikasi Kecerdasan Buatan
• Pathfnder (Heckerman,
1992): diagnosis of lymph
node disease.
• Perception: Symptom
patients, test result
• Reasoning: Bayesian
inference, machine
learning.
• Action: suggest tests,
make diagnosis.
10/31/2018
Hal.
27
Aplikasi Kecerdasan Buatan
• COBOT (Isbell et al, 2000): learning
chatbot in LambdaMOO
• Percepts: what users are present,
how experienced they are, how
much they interact with each other,
what they do with each other,
things being said...
• Actions: “verbs” that express
actions on others and on objects –
but restricted to a few
• E.g. proposing a conversation topic,
introducing two users to each other,
giving a piece of information
• Goals: maximize reward received
from other users
10/31/2018
Hal.
28
Aplikasi Kecerdasan Buatan
• Brain image analysis (T.
Mitchell, 2008)
• Perception: brain imaging
using fMRI technology
• Action: detect which word
(e.g. “hammer”,
“apartment”, ...) is read by
the person
• Reasoning: machine
learning
10/31/2018
Hal.
29
Aplikasi Kecerdasan Buatan
• ALVINN (D. Pomerleau, CMU,
1995): drives autonomously
on the highway at 55 mph,
for 21 miles
• Perception: digitized camera
image of the road
• Actions: 64 diferent steering
angles
• Reasoning: artifcial neural
network trained with Back
Propagation
10/31/2018
Hal.
30
Tugas Minggu 1
• “NONTON” Film atau Video dengan topik
Kecerdasan Buatan.
• Tugas Anda:
▫ Judul video/flm,
▫ Aktor utama/spaker,
▫ Deskripsi singkat kategori AI yang digunakan
(bisa lebih dari satu),
▫ Kelebihan/kekurangan, dan saran anda,
▫ Jelaskan teknologi sejenis (kalo sudah ada).
• Laporan ditulis perseorangan, pada kertas A4,
tulis tangan, rapi dan mudah dibaca.
• Pengumpulan: pertemuan selanjutnya!
10/31/2018
Hal.
31
Silabus
• Bagian I: Making Decisions
▫ Search & planning
▫ Knowledge Representation
• Bagian II: Reasoning under Uncertainty
▫ Bayes’ nets
▫ Fuzzy System
▫ Machine learning
• Overview: Applications
▫ Aplikasi dari Kecerdasan Buatan
10/31/2018
Hal.
32
Further Courses in AI
• Introduction to Neural Networks and Machine
Learning
• Machine Learning and Data Mining
• Pattern Recognition
• Uncertainty and Learning in Artifcial
Intelligence
• Image Understanding
• Computational Linguistics
• Knowledge Representation and Reasoning
• Computational Vision
10/31/2018
Hal.
33
-- End --
10/31/2018