Artificial Intelligence (AI)

Introduction
 Shintami Chusnul Hidayati, Ph.D.
About the Lecture Department of Informatics, ITS

[email protected]

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

 Artificial Intelligence
IF185999
3 credits
About the Course
Thursday
1:30 – 4:00 PM

TIF112
Zoom meeting room

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

Textbooks

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

Learning Outcome
1. Students master the concept of artificial intelligence and able to identify problems that
can be solved by utilizing intelligent agents.
2. Students are able to explain, identify, design and implement intelligent agents for
appropriate problems by utilizing search algorithms, which include uninformed search,
informed search, heuristic search, adversarial search and search algorithms for
Constraint Satisfaction Problems.
3. Students are able to explain, design, and implement knowledge-based intelligent agents
by representing knowledge-based into propositional logic or first order logic and
utilizing resolution, forward, and backward chaining algorithms to perform the
inference process.
4. Students are able to explain, design and apply intelligent agents for problems that are
in conditions of uncertainty using Bayesian networks and probabilistic reasoning.

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

Topics
• Intelligent agent
• Uniformed search
• Informed search
• Local search and optimization
• Adversarial search
• Constraint Satisfaction Problem
• Reasoning: Propositional Logic
• Reasoning: First Order Logic
• Reasoning: Inference First Order Logic
• Learning Probabilistic (Bayesian Network)

www.its.ac.id IF184403 - Shintami C. Hidayati INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
What the class will look like
• Paper Review: 40%
• 𝟑×
• Final Project: 60%
• Proposal
• Progress
• Final presentation

www.its.ac.id IF184403 - Shintami C. Hidayati INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
What is intelligence?
• Intelligence:
• “the capacity to learn and solve problems” (Websters dictionary)
• in particular,
• the ability to solve novel problems
• the ability to act rationally
• the ability to act like humans
• Artificial Intelligence
• build and understand intelligent entities or agents
• 2 main approaches: “engineering” versus “cognitive modeling”

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

What is Artificial Intelligence (AI)?
• AI is the study of ideas that enable computers to be intelligent
• Intelligence might be defined as the capacity to acquire and apply
knowledge
• AI is the part of computer science concerned with design of computer
systems that exhibit human intelligence

www.its.ac.id IF184403 - Shintami C. Hidayati INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
What is involved in AI?
• Ability to interact with the real world
• to perceive, understand, and act
• e.g., speech recognition and understanding and synthesis
• Reasoning and planning
• modelling the external world, given input
• solving new problem, planning
• Learning and adaptation
• we are continuously learning and adapting
• our internal models are always being “updated”

www.its.ac.id IF184403 - Shintami C. Hidayati INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
Academic disciplines relevant to AI
Logic, methods of reasoning, mind as physical
Philosophy system, foundations of learning, language, rationality

Formal representation and proof, algorithms,

Mathematics computation, (un)decidability, (in)tractability

Probability/statistics modeling uncertainty, learning from data

Economics utility, decision theory, rational economic agents

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

Academic disciplines relevant to AI

Neuroscience neurons as information processing units

how people behave, perceive, process information,

Psychology/cognitive science represent knowledge

Computer engineering building fast computers

design systems that maximize an objective function

Control theory over time

Linguistics knowledge representation, grammars

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

History of AI

1943: early 1950s: initial 1955 - 1965: “great

1950: Turing 1956: birth of AI
beginnings promise enthusiasm”
• McCulloch & • Turing's • Dartmouth • Early AI • Newell and
Pitts: Boolean "Computing meeting: programs, Simon: GPS,
circuit model of Machinery and "Artificial including general problem
brain Intelligence“ Intelligence“ Samuel's solver
name adopted checkers program • Gelertner:
and Newell & Geometry
Simon's Logic Theorem Prover
Theorist • McCarthy:
invention of LISP

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

History of AI

1966–1973 1986 1995

Reality dawns Rise of machine learning AI as Science
• Realization that many AI problems are • Neural networks return to popularity • Integration of learning, reasoning, knowledge
intractable • Major advances in machine learning algorithms representation
• Limitations of existing neural network methods and applications • AI methods used in vision, language, data
identified mining, etc.

Adding domain knowledge

• Development of knowledge-based systems Role of uncertainty
• Success of rule-based expert systems, e.g., • Bayesian networks as a knowledge
DENDRAL, MYCIN representation framework

1969–1985 1990

IF184403 - Shintami C. Hidayati 16

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
 How can you tell whether a machine
or program is intelligent?

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

The touring test

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

The touring test

https://youtu.be/GZ5Oryle4yA

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

Applications of AI

Natural
Language Speech
Processing recognition
(NLP)

Computer
Humanoid
vision

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

Natural language processing

• Goal:
• enable people and computers to communicate in a natural (humanly)
language (such as English) rather than in a computer language
• Fields:
• Natural language understanding • Natural language generation
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
Speech recognition

• The primary interactive method of communication used by humans is not

reading and writing, it is speech
• The goal of speech recognition research is to allow computers to understand
human speech
• They can hear our voices and recognize the words we are speaking

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

Computer vision

• People generally use vision as their primary means of sensing their

environment
• We generally see more than we hear, feel or smell or taste
• The goal of computer vision research is to give computers this same
powerful facility for understanding their surrounding
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
Humanoid/robot
• A humanoid robot is a robot with its body
shape built to resemble the human body
• The design may be for functional
purposes, such as interacting with human
tools and environments, for experimental
purposes

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

Merits of AI
• They don’t stop
• No risk of harms
• Act as aids
• Their function is almost limitless

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

Demerits of AI
• Over reliance on AI
• Human feel
• Inferior
• Misuse

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

What we have done…

Fashion Analysis Popularity Prediction Visual Recognition

Video Analysis Biometrics Biomedical Computing

www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia

 Clothing genre classification
Goal:
Recognize the genre of clothes based on a set of visually differentiable style elements
Genre Collar Front button Print style Shoulder Sleeve
skin

Shintami Chusnul Hidayati, Chuang-Wen You, Wen-Huang Cheng, and Kai-Lung Hua, "Learning and Recognition of Clothing Genres from Full-body Images," IEEE
Transactions on Cybernetics, vol. 48, no. 5, pp. 1647 - 1659, 2018.
Shintami Chusnul Hidayati, Wen-Huang Cheng, and Kai-Lung Hua, "Clothing Genre Classification by Exploiting the Style Elements," in Proceedings of the 20th
ACM International Conference on Multimedia (ACM MM), Nara, Japan, Oct. 29 - Nov. 2, 2012.
Shintami Chusnul Hidayati, Kai-Lung Hua, and Wen-Huang Cheng, "On the Discovery of Computable Visual Features for Human Garments Detection," in
Proceedings of the 25th IPPR Conference on Computer Vision, Graphics, and Image Processing (CVGIP), Aug. 12 - 14, 2012.1
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
Clothing recognition
Goal:
Discover clothing region in an image and recognize its genre

What kind of clothes in this image? Long-sleeves T-Shirt

Shintami Chusnul Hidayati, Kai-Lung Hua, Yu Tsao, Jiaying Liu, Hong-Han Shuai, and Wen-Huang Cheng, "Garment Detectives: Discovering Clothes and Its
Genre in Consumer Photos," in Proceedings of the IEEE International Conference on Multimedia Information Processing and Retrieval (IEEE MIPR), San Jose,
California, USA, Mar. 28 - 30, 2019.
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
 Fashion trend spotting
Goal:
Discover the trending styles for a specific season of fashion week events

Color Cut Layering

Shintami Chusnul Hidayati, Kai-Lung Hua, Wen-Huang Cheng, and Shih-Wei Sun, "What are the Fashion Trends in New York?," in Proceedings of the 22nd ACM
International Conference on Multimedia (ACM MM), Orlando, Florida, USA, Nov. 3 - 7, 2014.
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
 Fashion style recommendation
“The dress must follow the body of a woman, not the body following the
shape of the dress”
− Hubert de Givenchy, fashion designer

Shintami Chusnul Hidayati, Cheng-Chun Hsu, Yu-Ting Chang, Kai-Lung Hua, Jianlong Fu, and Wen-Huang Cheng, "What dress fits me best? Fashion
Recommendation on the Clothing Style for Personal Body Shape," in Proceedings of the 28th ACM International Conference on Multimedia (ACM MM), Seoul, Korea,
Oct. 22 - 26, 2018.
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
 Popularity prediction
Goal: A low-popularity image A high-popularity image
Predict the popularity of an image that
will receive on social media

Shintami Chusnul Hidayati, Yi-Ling Chen, Chao-Lung Yang, and Kai-Lung Hua, "Popularity Meter: An Influence- and Aesthetics-aware Social Media Popularity
Predictor," in Proceedings of the ACM International Conference on Multimedia (ACM MM), Mountain View, CA, USA, Oct. 23 - 27, 2017.
Eric Massip, Shintami Chusnul Hidayati, Wen-Huang Cheng, and Kai-Lung Hua, "Exploiting Category-specific Information for Image Popularity Prediction in Social
Media," in Proceedings of the IEEE International Conference on Multimedia and Expo (ICME) Workshops, San Diego, USA, Jul. 23 - 27, 2018.
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
Biomedical computing
Goal:
Classify the malignant or benign nature of
lung nodules without actually computing the
morphology and texture features

Kai-Lung Hua, Che-Hao Hsu, Shintami Chusnul Hidayati, Wen-Huang Cheng, and Yu-Jen Chen, "Computer-Aided Classification of Lung Nodule on Computed
Tomography Images via Deep Learning Technique," OncoTargets and Therapy, vol. 2015:8, pp. 2015 - 2022, 2015.
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
Biometrics
Goal:
Recognize cats by exploiting their
noses that are believed to be a
unique identifier

Yu-Chen Chen, Shintami Chusnul Hidayati, Wen-Huang Cheng, Min-Chun Hu, and Kai-Lung Hua, "Locality Constrained Sparse Representation for Cat
Recognition," in Proceedings of the 22nd International Conference on MultiMedia Modeling (MMM), Miami, USA, Jan. 4 - 6, 2016.
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
Human action recognition
Goal:
Mine the most representative videos for each
semantic concept as its iconic movements

Yung-Huan Hsieh, Shintami Chusnul Hidayati, Wen-Huang Cheng, Min-Chun Hu, and Kai-Lung Hua, "Who's the Best Charades Player?: Mining Iconic
Movement of Semantic Concept," in Proceedings of the 20th International Conference on MultiMedia Modeling (MMM), Dublin, Ireland, Jan. 6 - 10, 2014.
Shintami Chusnul Hidayati, Che-Hao Hsu, Yung-Huan Hsieh, Min-Chun Hu, Wen-Huang Cheng, and Kai-Lung Hua, "Judge You by Your Actions: Performance
Talent Assessment with Depth Camera," in Proceedings of the 26th IPPR Conference on Computer Vision, Graphics, and Image Processing (CVGIP), Yilan, Taiwan,
Aug. 18 - 20, 2013.
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
Scene categorization
Goal:
Understand natural images based on its context

Dang Duy Thang, Shintami Chusnul Hidayati, Yung-Yao Chen, Wen-Huang Cheng, Shih-Wei Sun, and Kai-Lung Hua, "A Spatial-pyramid Scene Categorization
Algorithm based on Locality-aware Sparse Coding," in Proceedings of the 2016 IEEE International Conference on Multimedia Big Data (BigMM), Taipei, Taiwan,
Apr. 20 - 22, 2016.
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
3d model retrieval
Goal:
A feature-based 3D retrieval
method

Zhao-Ming Liu, Yung-Yao Chen, Shintami Chusnul Hidayati, Shih-Che Chien, Feng-Chia Chang, and Kai-Lung Hua, "3D Model Retrieval Based on Deep
Autoencoder Neural Networks," in Proceedings of the IEEE International Conference on Signals and Systems (ICSigSys), Bali, Indonesia, May 16 - 18, 2017.
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
Photo time estimation
Goal:
Compute the time information of outdoor photos by exploiting the temporal
relationship among multiple photos and the sun position in the sky

Tsung-Hung Tsai, Wei-Chih Jhou, Wen-Huang Cheng, Min-Chun Hu, I-Chao Shen, Tekoing Lim, Kai-Lung Hua, Ahmed Ghoneim, M. Anwar Hossain,
and Shintami Chusnul Hidayati, "Photo sundial: Estimating the Time of Capture in Consumer Photos," Neurocomputing, vol. 177, pp. 529 - 542, 2016.
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
Object tracking
Goal:
Estimate the pose of a hand in each consecutive frame

Jordi Sanchez-Riera, Shintami Chusnul Hidayati, Kai-Lung Hua, Jen-Chieh Chiang, and Wen-Huang Cheng, "A Learning-based Tracking Algorithm for Hand
Gesture," in Proceedings of the 29th IPPR Conference on Computer Vision, Graphics, and Image Processing (CVGIP), Keelung, Taiwan, Aug. 15 - 17, 2016.
Jordi Sanchez-Riera, Kai-Lung Hua, Yuan-Sheng Hsiao, Tekoing Lim, Shintami Chusnul Hidayati, and Wen-Huang Cheng, "A Comparative Study of Data Fusion
for RGB-D Based Visual Recognition," Pattern Recognition Letters, vol. 73, pp. 1 - 6, 2016.
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
 Color demosaicking
Goal:
Reconstruct a full color image from the incomplete color samples output from an
image sensor overlaid with a color filter array
1 color value for 1 color pixel

Kai-Lung Hua, Shintami Chusnul Hidayati, Fang-Lin He, Chia-Po Wei, and Yu-Chiang Frank Wang, "Context-Aware Joint Dictionary Learning for Color Image
Demosaicking," Journal of Visual Communication and Image Representation, vol. 38, pp. 230-245, 2016. (Impact Factor 2016: 2.164)
www.its.ac.id INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia
 Do you believe artificial intelligence
benefits mankind (yes) or detracts
from it (no)?

www.its.ac.id IF184403 - Shintami C. Hidayati INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia41
 Thank you!

www.its.ac.id IF184403 - Shintami C. Hidayati INSTITUT TEKNOLOGI SEPULUH NOPEMBER, Surabaya - Indonesia42