| Semester | Course Unit Code | Course Unit Title | T+P+L | Credit | Number of ECTS Credits | Last Updated Date |
| 8 | BLMS431 | Advanced Deep Learning | 3+0+0 | 3 | 5 | 13.10.2025 |
|
Language of Instruction
|
Turkish
|
|
Level of Course Unit
|
Bachelor's Degree
|
|
Department / Program
|
Computer Engineering
|
|
Type of Program
|
Formal Education
|
|
Type of Course Unit
|
Elective
|
|
Course Delivery Method
|
Face To Face
|
|
Objectives of the Course
|
The aim of the course is to prepare the student to conduct advanced research and develop applications in deep learning.
|
|
Course Content
|
Theoretical parts of artificial neural networks, deep learning algorithms, computer vision with Python Keras and application development approaches on text data.
|
|
Course Methods and Techniques
|
|
|
Prerequisites and co-requisities
|
None
|
|
Course Coordinator
|
Asist Prof. Ümit Öztürk
|
|
Name of Lecturers
|
Undefined Engin SEVEN
|
|
Assistants
|
None
|
|
Work Placement(s)
|
No
|
Recommended or Required Reading
|
Resources
|
Deep Learning with Python, 2nd ed. François Chollet veya Türkçe çevirisi: Python ile Derin Öğrenme, François Chollet 2. Baskı
Introduction to Machine Learning, Ethem Alpaydın
Yapay Zeka, Dr. Atınç Yılmaz
|
Course Category
|
Mathematics and Basic Sciences
|
%20
|
|
|
Engineering
|
%40
|
|
|
Field
|
%40
|
|
|
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
|
In-Term Studies
|
|
Mid-terms
|
1
|
%
35
|
|
Practice
|
1
|
%
15
|
|
Final examination
|
1
|
%
50
|
|
Total
|
3
|
%
100
|
ECTS Allocated Based on Student Workload
|
Activities
|
Total Work Load
|
|
Course Duration
|
14
|
3
|
42
|
|
Hours for off-the-c.r.stud
|
14
|
1
|
14
|
|
Presentation
|
1
|
10
|
10
|
|
Mid-terms
|
1
|
30
|
30
|
|
Final examination
|
1
|
30
|
30
|
|
Total Work Load
| |
|
Number of ECTS Credits 5
126
|
Course Learning Outcomes: Upon the successful completion of this course, students will be able to:
| No | Learning Outcomes |
|
1
| Yapay sinir ağı modelinin teorisinden anlar ve modeli uygular. |
|
2
| Derin öğrenme ve makine öğrenmesi temellerini kavrar. |
|
3
| Doğal dil işleme teorisini anlar ve modeli uygular. |
|
4
| . |
|
5
| Dil Modellerini uygular |
|
6
| Biçimbilimsel analiz ve Sözdizimsel analiz teorisini anlar |
|
7
| Büyük Dil Modelleri algoritmalarını uygular |
Weekly Detailed Course Contents
| Week | Topics | Study Materials | Materials |
| 1 |
Deep learning concept
|
|
|
| 2 |
Artificial Neural Network (Theoretical)
|
|
|
| 3 |
Artificial Neural Network (Theoretical)
|
|
|
| 4 |
Libraries and data structures for mathematical basis.
|
|
|
| 5 |
Implementation of a neural network.
|
|
|
| 6 |
Convolutional neural network - CNN (Theoretical)
|
|
|
| 7 |
The implementation of CNN algorithm for computer vision - 1
|
|
|
| 8 |
Implementation of CNN algorithm for computer vision - 2
|
|
|
| 9 |
Recurrent Neural Networks (RNN - Theoretical)
|
|
|
| 10 |
LSTM (Theoretical)
|
|
|
| 11 |
Transforming of text data.
|
|
|
| 12 |
Implemention of RNN
|
|
|
| 13 |
Implemention of LSTM
|
|
|
| 14 |
Gated Recurrent Unit (GRU) (Theoretical and implementation)
|
|
|
Contribution of Learning Outcomes to Programme Outcomes
bbb
https://obs.gedik.edu.tr/oibs/bologna/progCourseDetails.aspx?curCourse=243280&curProgID=5607&lang=en