Information Package / Course Catalogue
Deep Learning
Course Code: RYZ112
Course Type: Area Elective
Couse Group: Short Cycle (Associate's Degree)
Education Language: Turkish
Work Placement: N/A
Theory: 2
Prt.: 0
Credit: 2
Lab: 0
ECTS: 3
Objectives of the Course

The goal of this course is to teach students how to work with deep learning techniques, a sub-branch of artificial intelligence and machine learning, and to show them how to apply these methods to real-world problems.

Course Content

The Deep Learning course covers the fundamentals of artificial neural networks and deep learning techniques, providing students with the ability to create applied deep learning models.

Name of Lecturer(s)
Lec. İsmail MERSİNKAYA
Learning Outcomes
1.Gaining the ability to understand and apply the fundamentals of artificial neural networks.
2.Understanding of deep learning models such as convolutional and recursive neural networks.
3.Learn the techniques needed to train and evaluate deep learning models.
4.Develop the ability to successfully apply deep learning techniques in image processing, natural language processing, and other application areas.
5.Problem Solving and Analytical Thinking
Recommended or Required Reading
1."Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
2.Introduction to Deep Learning From Logical Calculus to Artificial Intelligence, Sandro Skansi
Weekly Detailed Course Contents
Week 1 - Theoretical
Basic Concepts
Week 2 - Theoretical
Artificial Neural Networks and Backpropagation Algorithm
Week 3 - Theoretical
Convolutional Neural Networks
Week 4 - Theoretical
Deep Natural Language Processing
Week 5 - Theoretical
Recurrent Neural Networks
Week 6 - Theoretical
Training and Evaluation of Deep Learning Models
Week 7 - Theoretical
Activation Functions and Loss Functions
Week 8 - Theoretical
Deep Learning Applications: Image Classification
Week 9 - Theoretical
Deep Learning Applications: Object Recognition
Week 10 - Theoretical
Deep Learning Applications: Sentiment Analysis and Text Classification
Week 11 - Theoretical
Deep Learning Applications: Voice Recognition
Week 12 - Theoretical
Transfer Learning and Model Improvement
Week 13 - Theoretical
Deep Learning and Ethical Issues
Week 14 - Theoretical
Deep Learning Application and Project
Assessment Methods and Criteria
Type of AssessmentCountPercent
Midterm Examination1%40
Final Examination1%60
Workload Calculation
ActivitiesCountPreparationTimeTotal Work Load (hours)
Lecture - Theory140228
Assignment50315
Individual Work140228
Midterm Examination1011
Final Examination1011
TOTAL WORKLOAD (hours)73
Contribution of Learning Outcomes to Programme Outcomes
PÇ-1
PÇ-2
PÇ-3
PÇ-4
PÇ-5
PÇ-6
PÇ-7
PÇ-8
PÇ-9
PÇ-10
PÇ-11
PÇ-12
PÇ-13
PÇ-14
PÇ-15
OÇ-1
5
5
5
5
5
5
5
5
5
5
5
5
5
5
5
OÇ-2
5
5
5
5
5
5
5
5
5
5
5
5
5
5
5
OÇ-3
5
5
5
5
5
5
5
5
5
5
5
5
5
5
5
OÇ-4
5
5
5
5
5
5
5
5
5
5
5
5
5
5
5
OÇ-5
5
5
5
5
5
5
5
5
5
5
5
5
5
5
5
Adnan Menderes University - Information Package / Course Catalogue
2026