COMPUTER ENGINEERING (MASTER) (WITHOUT THESIS)
Master	TR-NQF-HE: Level 7	QF-EHEA: Second Cycle	EQF-LLL: Level 7

Ders Genel Tanıtım Bilgileri

Course Code:

BMB 528

Ders İsmi:

Artificial Learning

Ders Yarıyılı:

Fall

Ders Kredileri:

Theoretical	Practical	Credit	ECTS
3	0	3	9

Language of instruction:

Ders Koşulu:

Ders İş Deneyimini Gerektiriyor mu?:

Type of course:

Bölüm/Fakülte 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 IŞIL GÜZEY

Course Lecturer(s):

Course Assistants:

Dersin Amaç ve İçeriği

Course Objectives:	The aim of this course is to provide students with the conceptual knowledge of machine learning and the ability to apply model training and subsequent performance evaluation techniques using Python language.
Course Content:	This course covers basic machine learning concepts, learning algorithms, model development and performance evaluation techniques. Python programming language is used in the application part of the course.

Learning Outcomes

The students who have succeeded in this course;

Learning Outcomes

1 - Knowledge
Theoretical - Conceptual
1) Perceives the position of machine learning within the field of artificial intelligence and its connection with statistics.
2) Learn the basic concepts of machine learning.
2 - Skills
Cognitive - Practical
1) Apply Python programming language for data analysis, model training, evaluation of trained model performance and explanation of model decision making logic.
3 - Competences
Communication and Social Competence
Learning Competence
Field Specific Competence
1) Learn the concepts of ethical and legal dimensions of Artificial Intelligence.
Competence to Work Independently and Take Responsibility

Ders Akış Planı

Week	Subject	Related Preparation
1)	-What is Machine Learning? - Machine Learning Stages -Data Types -Types of Learning -Model Training and Testing -Test Methods -Model Performance Metrics - Problems in Machine Learning - Underfitting - Overfitting - Curse of Dimensionality
2)	Machine Learning Integrated Development Environments (IDE) and Libraries - Pycharm, Spyder, Jupyter, Google Colab - Numpy, Pandas, Matplotlib, Scikit-Learn - Data Analytics and Attribute Engineering	Presentations on the subject and studies from supporting sources. Coding studies in the relevant language.
3)	Supervised Machine Learning Algorithms -Prediction - Linear Regression - Multiple Linear Regression - Evaluation of Methods	Presentations on the subject and studies from supporting sources. Coding studies in the relevant language.
4)	Supervised Machine Learning Algorithms -Classification-1 - Logistic Regression - K Nearest Neighbour - Naive Bayes	Presentations on the subject and studies from supporting sources. Coding studies in the relevant language.
5)	Supervised Machine Learning Algorithms -Classification-2 - Decision Tree - Ensemble Learning and Random Forest	Presentations on the subject and studies from supporting sources. Coding studies in the relevant language.
6)	Supervised Machine Learning Algorithms - Classification-3 - Support Vector Machine (SVM) - SVM and Kernel Trick	Presentations on the subject and studies from supporting sources. Coding studies in the relevant language.
7)	Evaluation of Classification Algorithms Review of general topics before the midterm exam, in-class question and answer studies	Presentations on the subject and studies from supporting sources. Coding studies in the relevant language.
8)	Midterm	Presentations on the subject and studies from supporting sources. Coding studies in the relevant language.
9)	Unsupervised Machine Learning Algorithms-1 - Clustering - K-Means	Presentations on the subject and studies from supporting sources. Coding studies in the relevant language.
10)	Unsupervised Machine Learning Algorithms-2 -Dimension Reduction - PCA - LDA	Presentations on the subject and studies from supporting sources. Coding studies in the relevant language.
11)	Artificial Intelligence Ethics and Regulations	Konuyla ilgili ortak sunumlar ve yardımcı kaynaklardan çalışmalar.
12)	Explainable Artificial Intelligence - Interpretable Models - Post-hoc Explainability Methods - Model Independent Methods	Presentations on the subject and studies from supporting sources. Coding studies in the relevant language.
13)	Homework Presentations
14)	Review of general topics before the final exam, in-class question and answer studies	Presentations on the subject and studies from supporting sources. Coding studies in the relevant language.

Sources

Course Notes / Textbooks:

1 - Makine Öğrenmesi Algoritmaları, Editör: Prof. Dr. Murat Gök, Nobel Yayıncılık

2 - Scikit-Learn, Keras ve TensorFlow ile Uygulamalı Makine Öğrenmesi;Akıllı Sistemler Geliştirmek İçin Konseptler, Araçlar ve Teknikler, Aurelien Geron, Buzdağı Yayınevi (https://github.com/ageron/handson-ml2 )

3 - Makine Öğrenmesi Teorik Yönleri ve Python Uygulamaları ile Bir Yapay Zeka Ekolü, Doç. Dr. Sinan UĞUZ, 2023, Nobel Yayıncılık

4 - https://www.btkakademi.gov.tr/portal/course/python-ile-makine-ogrenmesi-11800

5- https://www.btkakademi.gov.tr/portal/course/veri-bilimi-icin-python-ve-tensorflow-11705

6- Explanatory Model Analysis - https://ema.drwhy.ai/

7- Interpretable Machine Learning - A Guide for Making Black Box Models Explainable

References:

Ders - Program Öğrenme Kazanım İlişkisi

Ders Öğrenme Kazanımları	1	2	3	4
Program Outcomes
1) Having comprehensive knowledge in information systems development, including planning, analysis, design and configuration stages, and familiarity with relevant development methods and modeling tools.
2) Having comprehensive knowledge to perform advanced applications in the field of computer engineering.
3) Ability to access, evaluate and apply information by conducting applied research in the field of Information and Communication Technologies, and integrate information from different disciplines.
4) Discovering, drawing conclusions, sharing and applying knowledge with scientific methods in different fields; Relating information from different disciplines.
5) Ability to independently carry out a study that requires expertise in the field of information technologies.
6) Ability to develop new strategic approaches to solve unforeseen complex problems encountered in applications related to the field of Information and Communication Technologies and to produce solutions by taking responsibility.
7) Ability to take leadership in environments that require solving problems related to the field of Information and Communication Technologies.
8) To be able to critically evaluate the expert knowledge and skills acquired in the field of Computer Engineering and to direct his/her learning.
9) Being aware of current studies in the field of Computer Engineering, constantly following the developments, examining and naming them when necessary.
10) Communicating effectively verbally and in writing in Turkish and English.
11) Observing social, scientific and ethical values in their work.
12) Ability to develop strategies, policies and implementation plans on issues related to Information Technologies and evaluate the results obtained within the framework of quality processes.
13) Ability to use the knowledge, problem solving and/or application skills they have absorbed in the field of Computer Engineering in interdisciplinary studies.

Ders - Öğrenme Kazanımı İlişkisi

No Effect	1 Lowest	2 Low	3 Average	4 High	5 Highest

	Program Outcomes	Level of Contribution
1)	Having comprehensive knowledge in information systems development, including planning, analysis, design and configuration stages, and familiarity with relevant development methods and modeling tools.
2)	Having comprehensive knowledge to perform advanced applications in the field of computer engineering.
3)	Ability to access, evaluate and apply information by conducting applied research in the field of Information and Communication Technologies, and integrate information from different disciplines.
4)	Discovering, drawing conclusions, sharing and applying knowledge with scientific methods in different fields; Relating information from different disciplines.
5)	Ability to independently carry out a study that requires expertise in the field of information technologies.
6)	Ability to develop new strategic approaches to solve unforeseen complex problems encountered in applications related to the field of Information and Communication Technologies and to produce solutions by taking responsibility.
7)	Ability to take leadership in environments that require solving problems related to the field of Information and Communication Technologies.
8)	To be able to critically evaluate the expert knowledge and skills acquired in the field of Computer Engineering and to direct his/her learning.
9)	Being aware of current studies in the field of Computer Engineering, constantly following the developments, examining and naming them when necessary.
10)	Communicating effectively verbally and in writing in Turkish and English.
11)	Observing social, scientific and ethical values in their work.
12)	Ability to develop strategies, policies and implementation plans on issues related to Information Technologies and evaluate the results obtained within the framework of quality processes.
13)	Ability to use the knowledge, problem solving and/or application skills they have absorbed in the field of Computer Engineering in interdisciplinary studies.

Öğrenme Etkinliği ve Öğretme Yöntemleri

Anlatım
Beyin fırtınası /Altı şapka
Bireysel çalışma ve ödevi
Course
Okuma
Homework
Problem Çözme
Soru cevap/ Tartışma

Ölçme ve Değerlendirme Yöntemleri ve Kriterleri

Yazılı Sınav (Açık uçlu sorular, çoktan seçmeli, doğru yanlış, eşleştirme, boşluk doldurma, sıralama)
Homework

Assessment & Grading

Semester Requirements	Number of Activities	Level of Contribution
Attendance	14	% 0
Homework Assignments	1	% 20
Midterms	1	% 30
Final	1	% 50
total		% 100
PERCENTAGE OF SEMESTER WORK		% 50
PERCENTAGE OF FINAL WORK		% 50
total		% 100

İş Yükü ve AKTS Kredisi Hesaplaması

Activities	Number of Activities	Duration (Hours)	Workload
Course Hours	14	3	42
Study Hours Out of Class	12	3	36
Homework Assignments	1	20	20
Midterms	1	20	20
Final	1	32	32
Total Workload			150