Course Information

Semester	Course Unit Code	Course Unit Title	T+P+L	Credit	Number of ECTS Credits	Last Updated Date
4	CPP214	Deep Learning	2+2+0	3	4	27.04.2026

Course Details

Language of Instruction	Turkish
Level of Course Unit	Associate Degree
Department / Program	Computer Programming
Type of Program	Formal Education
Type of Course Unit	Elective
Course Delivery Method	Face To Face
Objectives of the Course	The objective of this course is to equip students with an understanding of the fundamental concepts and theoretical foundations of deep learning, as well as its role in modern artificial intelligence applications. The course aims to enable students to understand the working principles of various deep learning architectures and adapt these architectures to real-world problems. Additionally, the course aims to help students develop an analytical perspective on model design, training processes, and performance evaluation approaches.
Course Content	The course covers the fundamentals of artificial neural networks, advanced deep learning architectures, and learning algorithms. Current approaches such as convolutional neural networks, recurrent neural networks, and transformer-based models are examined both theoretically and practically. Additionally, topics such as data preprocessing, model optimization, overfitting issues, and performance metrics are supported by examples using real-world datasets.
Course Methods and Techniques	Face-to-face instruction, demonstration and practice.
Prerequisites and co-requisities	None
Course Coordinator	None
Name of Lecturers	Instructor ZEKİ ÇIPLAK zkcplk.medium.com
Assistants	None
Work Placement(s)	No

Recommended or Required Reading

Resources	Deep Learning with PyTorch: From Concepts to Applications, Assoc. Prof. Dr. Yılmaz KAYA, Akademisyen Publishing House
Course Notes

Course Category

Mathematics and Basic Sciences	%20
Engineering	%60
Engineering Design	%10
Field	%10

Planned Learning Activities and Teaching Methods

Activities are given in detail in the section of "Assessment Methods and Criteria" and "Workload Calculation"

Assessment Methods and Criteria

ECTS Allocated Based on Student Workload

Activities	Quantity	Duration	Total Work Load
Course Duration	14	4	56
Hours for off-the-c.r.stud	14	3	42
Mid-terms	1	1	1
Project	1	5	5
Total Work Load			Number of ECTS Credits 4 104

Course Learning Outcomes: Upon the successful completion of this course, students will be able to:

No	Learning Outcomes
1	It explains the fundamental concepts of deep learning, its historical development, and its role within machine learning.
2	It provides a comparative analysis of the working principles of various deep learning architectures (CNN, RNN, Transformer, etc.).
3	Designs, trains, and optimizes a deep learning model suitable for a given problem.
4	Evaluates the performance of deep learning models using appropriate metrics and interprets the results.
5	It discusses the ethical, computational cost, and scalability aspects of developing deep learning-based solutions using real-world datasets.

Weekly Detailed Course Contents

Week	Topics	Study Materials	Materials
1	Introduction to Deep Learning
2	The Basics of Artificial Neural Networks
3	Activation Functions and Loss Functions
4	Optimization Methods and Gradient Descent
5	Backpropagation Algorithm
6	Overfitting and Regularization Techniques
7	Convolutional Neural Networks (CNN)
8	Advanced CNN Architectures and Interm Evaluation
9	Recurrent Neural Networks (RNNs) and Sequential Data
10	LSTM and GRU Architectures
11	Attention Mechanisms and Transformer Models
12	Data Preprocessing and Model Evaluation in Deep Learning
13	Deep Learning Applications and Ethical Considerations
14	General Review, Current Research Trends, and Project Presentations

Contribution of Learning Outcomes to Programme Outcomes

bbb

https://obs.gedik.edu.tr/oibs/bologna/progCourseDetails.aspx?curCourse=280993&curProgID=44&lang=en