1. SECOND CYCLE - MASTER'S DEGREE
  2. THE GRADUATE SCHOOL OF NATURAL AND APPLIED SCIENCES
  3. COMPUTER ENGINEERING DEPARTMENT
  4. 1281 Computer Engineering
Course Information Course Learning Outcomes Course's Contribution To Program ECTS Workload Course Details
Print

COURSE INFORMATION
Course CodeCourse TitleL+P HourSemesterECTS
CENG 588DEEP LEARNING AND APPLICATIONS3 + 02nd Semester7,5

COURSE DESCRIPTION
Course Level Master's Degree
Course Type Elective
Course Objective 110/5000 Deep learning algorithms will be explained theoretically and practical applications will be realized through projects.
Course Content Regularization of deep or distributed models, optimization for training deep models, convolutional networks, sequence modeling: recurrent and recursive nets, structured probabilistic models for deep learning, linear factor models and auto-encoders
Prerequisites No the prerequisite of lesson.
Corequisite No the corequisite of lesson.

COURSE LEARNING OUTCOMES
1Expresses the arrangement of deep or distributed models.
2Applies the deep learning methods with a project.
3Optimizes for deep models.
4Defines iterative and recursive networks.
5Applies deep learning methods in real application areas.

COURSE'S CONTRIBUTION TO PROGRAM
PO 01PO 02PO 03PO 04PO 05PO 06PO 07PO 08PO 09PO 10PO 11PO 12
LO 001            
LO 002            
LO 003            
LO 004            
LO 005            
Sub Total            
Contribution000000000000

ECTS ALLOCATED BASED ON STUDENT WORKLOAD BY THE COURSE DESCRIPTION
ActivitiesQuantityDuration (Hour)Total Work Load (Hour)
Course Duration (14 weeks/theoric+practical)14342
Hours for off-the-classroom study (Pre-study, practice)14342
Mid-terms12121
Final examination14040
Report / Project15050
Total Work Load

ECTS Credit of the Course





195

7,5
COURSE DETAILS
 Select Year   


 Course TermNoInstructors
Details 2025-2026 Spring1SERDAR İPLİKÇİ


Print

Course Details
Course Code Course Title L+P Hour Course Code Language Of Instruction Course Semester Mode of Delivery
CENG 588 DEEP LEARNING AND APPLICATIONS 3 + 0 1 Turkish 2025-2026 Spring Face to Face
Course Coordinator  E-Mail  Phone Number  Course Location Attendance
Prof. Dr. SERDAR İPLİKÇİ iplikci@pau.edu.tr MUH A0233 MUH A0257 MUH A0313 %
Goals 110/5000 Deep learning algorithms will be explained theoretically and practical applications will be realized through projects.
Content Regularization of deep or distributed models, optimization for training deep models, convolutional networks, sequence modeling: recurrent and recursive nets, structured probabilistic models for deep learning, linear factor models and auto-encoders
Topics
WeeksTopics
1 Introduction/PyTorch Temelleri
2 PyTorch Temelleri
3 Lineer Regresyon
4 Lineer Regresyon
5 Lineer Sınıflandırma
6 Multi Layer Perceptron
7 Builders’ Guide for PyTorch
8 Convolutional Neural Networks
9 Modern Convolutional Neural Networks
10 Recurrent Neural Networks
11 Modern Recurrent Neural Networks
12 Attention Mechanisms and Transformers
13 Attention Mechanisms and Transformers
14 Attention Mechanisms and Transformers
Materials
Materials are not specified.
Resources
Course Assessment
Assesment MethodsPercentage (%)Assesment Methods Title
Final Exam50Final Exam
Midterm Exam50Midterm Exam
L+P: Lecture and Practice
PQ: Program Learning Outcomes
LO: Course Learning Outcomes