Course Information
SemesterCourse Unit CodeCourse Unit TitleT+P+LCreditNumber of ECTS CreditsLast Updated Date
1EEE 507Deep Learning3+0+03611.07.2024

 
Course Details
Language of Instruction English
Level of Course Unit Master's Degree
Department / Program ELECTRICAL AND ELECTRONICS ENGINEERING
Type of Program Formal Education
Type of Course Unit Elective
Course Delivery Method Face To Face
Objectives of the Course The aim of this course is to provide students the knowledge about the basic techniques and methodologies of deep learning and abilities to apply deep learning methods on practical problems.
Course Content Review of deep neural networks. Basic learning algorithms and architectures for deep learning. Convolutional neural networks. Sequence models. Auto-Encoders. Hyperparameters tuning, regularization and optimization.

Course Methods and Techniques
Prerequisites and co-requisities None
Course Coordinator Associate Prof.Dr. Serkan ÖZBAY
Name of Lecturers Associate Prof.Dr. SERKAN ÖZBAY
Assistants None
Work Placement(s) No

Recommended or Required Reading
Resources Lecture Notes
Course Notes Deep Learning
Charu C. Aggarwal
Springer International Publishing

Course Category
Mathematics and Basic Sciences %30
Engineering %50
Engineering Design %20

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 Quantity Percentage
Mid-terms 2 % 30
Project 1 % 30
Final examination 1 % 40
Total
4
% 100

 
ECTS Allocated Based on Student Workload
Activities Quantity Duration Total Work Load
Course Duration 14 3 42
Hours for off-the-c.r.stud 14 3 42
Mid-terms 2 26 52
Project 8 3 24
Final examination 1 20 20
Total Work Load   Number of ECTS Credits 6 180

 
Course Learning Outcomes: Upon the successful completion of this course, students will be able to:
NoLearning Outcomes
1 Understanding the fundamentals of deep learning.
2 Knowing the main techniques in deep learning and the main research in this field.
3 Evaluating the advantages and disadvantages of deep learning neural network architectures and other approaches.
4 Being able to design and implement deep neural network systems and solve real-world problems.
5 Performing regularization, training optimization, and hyperparameter selection on deep models.

 
Weekly Detailed Course Contents
WeekTopicsStudy MaterialsMaterials
1 Review of deep neural networks. Reading related lecture notes
2 Review of deep neural networks. Reading related lecture notes
3 Basic learning algorithms and architectures for deep learning. Supervised Learning Reading related lecture notes
4 Basic learning algorithms and architectures for deep learning. Unsupervised Learning Reading related lecture notes
5 Basic learning algorithms and architectures for deep learning. Reinforcement Learning Reading related lecture notes
6 Convolutional neural networks Reading related lecture notes
7 Convolutional neural networks Reading related lecture notes
8 Convolutional neural networks Reading related lecture notes
9 Sequence models Reading related lecture notes
10 Sequence models Reading related lecture notes
11 Auto-Encoders Reading related lecture notes
12 Auto-Encoders Reading related lecture notes
13 Hyperparameters tuning, regularization and optimization Reading related lecture notes
14 Hyperparameters tuning, regularization and optimization Reading related lecture notes

 
Contribution of Learning Outcomes to Programme Outcomes
P1 P2 P3 P4
All 4 4 4 2
C1 4 4 4 2
C2 4 4 4 2
C3 4 4 4 2
C4 4 4 4 2
C5 4 4 4 2

  bbb

  
  https://obs.gantep.edu.tr/oibs/bologna/progCourseDetails.aspx?curCourse=455332&lang=en