COMPUTER ENGINEERING (MASTER) (THESIS)
Qualification Awarded Program Süresi Toplam Kredi (AKTS) Öğretim Şekli Yeterliliğin Düzeyi ve Öğrenme Alanı
2 120 FULL TIME TYÇ, TR-NQF-HE, EQF-LLL, ISCED (2011):Level 7
QF-EHEA:Second Cycle
TR-NQF-HE, ISCED (1997-2013): 48,52

Ders Genel Tanıtım Bilgileri

Course Code: 3016002051
Ders İsmi: Special Topics in Artificial Intelligence
Ders Yarıyılı: Spring
Ders Kredileri:
Theoretical Practical Labs Credit ECTS
3 0 0 3 6
Language of instruction: TR
Ders Koşulu:
Ders İş Deneyimini Gerektiriyor mu?: No
Other Recommended Topics for the Course:
Type of course: Anabilim Dalı/Lisansüstü Seçmeli
Course Level:
Master TR-NQF-HE:7. Master`s Degree QF-EHEA:Second Cycle EQF-LLL:7. Master`s Degree
Mode of Delivery: Face to face
Course Coordinator : Dr.Öğr.Üyesi Recep DURANAY
Course Lecturer(s): Assoc. Prof. Oğuz ATA
Course Assistants:

Dersin Amaç ve İçeriği

Course Objectives: Gain an understanding of the following topics; 1. Finding suitable preprocessing methods to analyze raw data and make it usable, 2. Convolutional, repetitive and graph neural networks, long short-term memory and automatic as well as core techniques of AI such as search, expert systems, planning and information representation To introduce Deep Learning methods such as coders, 3. To understand the mathematical principles of optimization and regulation of deep learning methods, 4. To be able to design deep neural networks for various problems in artificial intelligence, 5. To apply solutions to learning problems using various deep neural network techniques.
Course Content: Learning Types • Introduction to Searching • Searching Algorithms • Rule-Based Expert Systems • Information representation • Automatic Planning • Multilayer Perceptrons, Feed Forward Neural Networks • Backpropagation, Activation Functions, Loss Functions, Optimization Methods, Performance Metrics • Convolutional Neural Networks • Recurrent Neural Networks Networks, Long-short-term memory networks • Autoencoders, Graphical Neural Networks, Transfer Learning

Learning Outcomes

The students who have succeeded in this course;
Learning Outcomes
1 - Knowledge
Theoretical - Conceptual
1) Gaining the ability to analyze raw data and apply necessary data preprocessing techniques.
2 - Skills
Cognitive - Practical
3 - Competences
Communication and Social Competence
Learning Competence
Field Specific Competence
1) The ability of AI agents to be used with conventional AI techniques for search and planning purposes.
Competence to Work Independently and Take Responsibility

Ders Akış Planı

Week Subject Related Preparation
1) Introduction: What is Artificial Intelligence? History and Background of AI. Artificial Intelligence Applications Textbook-
2) Yapay Zeka Tekniklerinin Tanıtılması: Uzman Sistemler ve genetik algoritmalara giriş, temel kavramlar, yapılar, bilgi-kural tabanı, çıkarım mekanizması -
2) Introduction of Artificial Intelligence Techniques: Introduction to Expert Systems and genetic algorithms, basic concepts, structures, knowledge-rule base, inference mechanism Textbook
3) Introduction to Search Algorithms and Basic Concepts Textbook
3) Arama Algoritmalarına Giriş ve Temel Kavramlar -
4) Arama Algoritmaları -
5) Rule-Based Expert Systems -
6) Automatic Scheduling -
7) Information Representation in AI Systems -
8) MIDTERM -
9) Multilayer Neural Networks, Feed Forward Neural Networks -
10) Backpropagation, Activation Functions, Loss Functions, Optimization Methods, Performance Metrics -
11) Convolutional Neural Networks -
12) Iterative Neural Networks, Long-Short-Term Memory Networks -
13) Autoencoders, Graph Neural Networks, Transfer Learning -
14) Project Presentations -
15) Project Presentations -
16) FINAL -

Sources

Course Notes / Textbooks: - Michael Negnevitsky, Artificial Intelligence: A Guide to Intelligent Systems, Addison Wesley
- Stuart Russel, Peter Norvig, Artificial Intelligence: A Modern Approach, Pearson
- Aston Zhang, et.al.: Dive Into Deep Learning
Ethem Alpaydın, Yapay Öğrenme, Boğaziçi Üniversitesi Yayınevi, 3. Baskı, 2017
- Ian Goodfellow, Yoshua Bengio and Aaron Courville: Deep Learning, MIT Press
- François Chollet: Deep Learning with Python, 2nd Ed. Manning Publications
- Paul Deitel & Harvey Deitel: Python for Programmers with introductory AI case studies
- Luca Pietro Giovanni Antiga, Thomas Viehmann, Eli Stevens: Deep Learning with Pytorch, Manning Publications
- Sebastian Raschka, Hayden Liu, Vahid Mirjalili: Machine Learning with PyTorch and Scikit-Learn, Manning Publications.
References: - Michael Negnevitsky, Artificial Intelligence: A Guide to Intelligent Systems, Addison Wesley
- Stuart Russel, Peter Norvig, Artificial Intelligence: A Modern Approach, Pearson
- Aston Zhang, et.al.: Dive Into Deep Learning
Ethem Alpaydın, Yapay Öğrenme, Boğaziçi Üniversitesi Yayınevi, 3. Baskı, 2017
- Ian Goodfellow, Yoshua Bengio and Aaron Courville: Deep Learning, MIT Press
- François Chollet: Deep Learning with Python, 2nd Ed. Manning Publications
- Paul Deitel & Harvey Deitel: Python for Programmers with introductory AI case studies
- Luca Pietro Giovanni Antiga, Thomas Viehmann, Eli Stevens: Deep Learning with Pytorch, Manning Publications
- Sebastian Raschka, Hayden Liu, Vahid Mirjalili: Machine Learning with PyTorch and Scikit-Learn, Manning Publications.

Ders - Program Öğrenme Kazanım İlişkisi

Ders Öğrenme Kazanımları

1

2

Program Outcomes
1) Ability to reach wide and deep knowledge through scientific research in the field of Computer Science and Engineering, evaluate, interpret and apply.
2) Ability to use scientific methods to cover and apply limited or missing knowledge, and to integrate the knowledge of different disciplines.
3) Ability to construct Computer Science and Engineering problems, develop methods to solve the problems and use innovative methods in the solution.
4) Ability to develop new and/or original ideas and algorithm; develop innovative solutions in the design of system, component or process.
5) Ability to have extensive knowledge about current techniques and methods applied in Computer Engineering and their constraints.
6) Ability to design and implement analytical modeling and experimental research, solve and interpret complex situations encountered in the process.
7) Ability to use a foreign language (English) at least at the level of European Language Portfolio B2 in verbal and written communication.
8) Ability to lead in multidisciplinary teams, develop solutions to complex situations and take responsibility.
9) Awareness of the social, legal, ethical and moral values, and the ability to conduct research and implementation work within the framework of these values.
10) Awareness of the new and emerging applications in Computer Science and Engineering field, and the ability to examine them and learn if necessary.

Ders - Öğrenme Kazanımı İlişkisi

No Effect 1 Lowest 2 Low 3 Average 4 High 5 Highest
           
Program Outcomes Level of Contribution
1) Ability to reach wide and deep knowledge through scientific research in the field of Computer Science and Engineering, evaluate, interpret and apply. 4
2) Ability to use scientific methods to cover and apply limited or missing knowledge, and to integrate the knowledge of different disciplines. 4
3) Ability to construct Computer Science and Engineering problems, develop methods to solve the problems and use innovative methods in the solution. 4
4) Ability to develop new and/or original ideas and algorithm; develop innovative solutions in the design of system, component or process. 4
5) Ability to have extensive knowledge about current techniques and methods applied in Computer Engineering and their constraints. 3
6) Ability to design and implement analytical modeling and experimental research, solve and interpret complex situations encountered in the process. 2
7) Ability to use a foreign language (English) at least at the level of European Language Portfolio B2 in verbal and written communication. 3
8) Ability to lead in multidisciplinary teams, develop solutions to complex situations and take responsibility. 4
9) Awareness of the social, legal, ethical and moral values, and the ability to conduct research and implementation work within the framework of these values. 3
10) Awareness of the new and emerging applications in Computer Science and Engineering field, and the ability to examine them and learn if necessary. 5

Öğrenme Etkinliği ve Öğretme Yöntemleri

Course
Labs
Okuma

Ölçme ve Değerlendirme Yöntemleri ve Kriterleri

Yazılı Sınav (Açık uçlu sorular, çoktan seçmeli, doğru yanlış, eşleştirme, boşluk doldurma, sıralama)
Sözlü sınav
Homework
Uygulama
Gözlem
Bireysel Proje

Assessment & Grading

Semester Requirements Number of Activities Level of Contribution
Homework Assignments 2 % 30
Midterms 1 % 30
Semester Final Exam 1 % 40
total % 100
PERCENTAGE OF SEMESTER WORK % 60
PERCENTAGE OF FINAL WORK % 40
total % 100

İş Yükü ve AKTS Kredisi Hesaplaması

Activities Number of Activities Duration (Hours) Workload
Course Hours 15 3 45
Study Hours Out of Class 15 5 75
Homework Assignments 2 30 60
Midterms 1 2 2
Final 1 3 3
Total Workload 185