Psychology
Bachelor	Length of the Programme: 4	Number of Credits: 240	TR-NQF-HE: Level 6	QF-EHEA: First Cycle	EQF: Level 6

Ders Genel Tanıtım Bilgileri

School/Faculty/Institute

Faculty of Engineering

Course Code

COMP 462

Course Title in English

Introduction to Machine Learning

Course Title in Turkish

Yapay Öğrenmeye Giriş

Language of Instruction

Type of Course

Flipped Classroom

Level of Course

Introductory

Semester

Fall

Contact Hours per Week

Lecture: 3

Recitation: None

Lab: None

Other: None

Estimated Student Workload

152 hours per semester

Number of Credits

6 ECTS

Grading Mode

Standard Letter Grade

Pre-requisites

None

Expected Prior Knowledge

Prior knowledge in programming, probability and statistics.

Co-requisites

None

Registration Restrictions

Only Undergraduate Students

Overall Educational Objective

To learn the fundamentals of machine learning methods and how to design and implement intelligent systems to make prediction, classification, and regression.

Course Description

This course covers the fundamentals of machine learning approaches: Supervised learning, unsupervised learning, regression methods, outlier detection, feature analysis, validation and evaluation.

Course Description in Turkish

Bu ders yapay öğrenmede kullanılan temel yöntemleri içermektedir: Gözetimli ve gözetimsiz öğrenme, bağlanım yöntemleri, aykırılık tespiti, öznitelik analizi, geçerleme ve performans değerlendirmesi

Course Learning Outcomes and Competences

Upon successful completion of the course, the learner is expected to be able to:
1) identify and solve a complex engineering problem using machine learning techniques;
2) design a machine learning system to produce solutions;
3) present the results of a machine learning solution to a range of audiences;
4) recognize ethical and professional responsibilities in creating the machine learning system;
5) analyze and interpret the data used for the machine learning system;
6) acquire and apply new knowledge of machine learning techniques;

Program Learning Outcomes/Course Learning Outcomes	1	2	3	4	5	6
1) Thorough knowledge of the major concepts, theoretical perspectives, empirical findings, and historical trends in psychology.
2) Understanding of and ability to apply essential research methods in psychology, including research design, data analysis, and data interpretation.
3) Competence to use critical and creative thinking, skeptical inquiry and a scientific approach to solving problems related to behavior and mental processes.
4) Understanding and ability to apply psychological principles, skills and values in personal, social, and organizational contexts.
5) Ability to weigh evidence, to tolerate ambiguity, and to reflect other values that underpin psychology as a discipline.
6) Internalization and dissemination of professional ethical standards.
7) Demonstration of competence in information technologies, and the ability to use computer and other technologies for purposes related to the pursuit of knowledge in psychology and the broader social sciences.
8) Skills to communicate the knowledge of psychological science effectively, in a variety of formats, in both Turkish and in English (in English, at least CEFR B2 level).
9) Recognition, understanding, and respect for the complexity of sociocultural and international diversity.
10) Recognition for the need for, and the skills to pursue, lifelong learning, inquiry, and self-improvement.
11) Ability to formulate critical hypotheses based on psychological theory and literature, and design studies to test those hypotheses.
12) Ability to acquire knowledge independently, and to plan one’s own learning.
13) Demonstration of advanced competence in the clarity and composition of written work and presentations.

Relation to Program Outcomes and Competences

N None	S Supportive	H Highly Related

	Program Outcomes and Competences	Level	Assessed by
1)	Thorough knowledge of the major concepts, theoretical perspectives, empirical findings, and historical trends in psychology.	N
2)	Understanding of and ability to apply essential research methods in psychology, including research design, data analysis, and data interpretation.	N
3)	Competence to use critical and creative thinking, skeptical inquiry and a scientific approach to solving problems related to behavior and mental processes.	H	Exam,HW,Participation
4)	Understanding and ability to apply psychological principles, skills and values in personal, social, and organizational contexts.	N
5)	Ability to weigh evidence, to tolerate ambiguity, and to reflect other values that underpin psychology as a discipline.	N
6)	Internalization and dissemination of professional ethical standards.	N
7)	Demonstration of competence in information technologies, and the ability to use computer and other technologies for purposes related to the pursuit of knowledge in psychology and the broader social sciences.	N
8)	Skills to communicate the knowledge of psychological science effectively, in a variety of formats, in both Turkish and in English (in English, at least CEFR B2 level).	N
9)	Recognition, understanding, and respect for the complexity of sociocultural and international diversity.	S	Participation
10)	Recognition for the need for, and the skills to pursue, lifelong learning, inquiry, and self-improvement.	S	HW,Participation
11)	Ability to formulate critical hypotheses based on psychological theory and literature, and design studies to test those hypotheses.	N
12)	Ability to acquire knowledge independently, and to plan one’s own learning.	S	Exam,HW
13)	Demonstration of advanced competence in the clarity and composition of written work and presentations.	H	Exam,HW

Prepared by and Date	YASSINE DRIAS , February 2023
Course Coordinator	TUBA AYHAN
Semester	Fall
Name of Instructor	Asst. Prof. Dr. TUNA ÇAKAR

Course Contents

Week	Subject
1)	Introduction to Machine Learning Concepts
2)	K Nearest Neighbor Algorithm
3)	Training, Testing and Validating Machine Learning Systems
4)	Clustering Techniques
5)	Decision Trees (Part 1)
6)	Decision Trees (Part 2)
7)	Gradient Descent Algorithm and Linear Regression
8)	Logistic Regression
9)	Feature Selection and Extraction Techniques
10)	Advanced Classification Methods
11)	Artificial Neural Networks (Part 1)
12)	Artificial Neural Networks (Part 2)
13)	Deep Learning Methods (Part 1)
14)	Deep Learning Methods (Part 2)
15)	Final Examination Period.
16)	Final Examination Period.

Required/Recommended Readings

Introduction to Machine Learning, Ethem Alpaydın, MIT Press, 3rd Edition (2015)

Teaching Methods

Flipped Classroom

Homework and Projects

Assignments

Laboratory Work

None

Computer Use

Required

Other Activities

None

Assessment Methods

Assessment Tools	Count	Weight
Homework Assignments	3	% 35
Project	1	% 30
Midterm(s)	1	% 35
TOTAL		% 100

Course Administration

driasy@mef.edu.tr

Instructor’s office: 5th floor Phone number: 0 212 395 37 45 Office hours: After the lecture hours. E-mail address: driasy@mef.edu.tr Rules for attendance: No attendance required. Statement on plagiarism: YÖK Regulations http://3fcampus.mef.edu.tr/uploads/cms/webadmin.mef.edu.tr/4833_2.pdf

ECTS Student Workload Estimation

Activity	No/Weeks	Hours			Calculation
	No/Weeks per Semester	Preparing for the Activity	Spent in the Activity Itself	Completing the Activity Requirements
Course Hours	14	1	3	1	70
Homework Assignments	4	1	14	2	68
Midterm(s)	1	10	2	2	14
Total Workload					152
Total Workload/25					6.1
ECTS					6