COURSE INTRODUCTION AND APPLICATION INFORMATION

Course Name
Deep Neural Networks
Code
Semester
Theory
(hour/week)
Application/Lab
(hour/week)
Local Credits
ECTS
CE 455
Fall/Spring
3
0
3
5
Prerequisites
None
Course Language
English
Course Type
Elective
Course Level
First Cycle
Mode of Delivery -
Teaching Methods and Techniques of the Course
Course Coordinator
Course Lecturer(s)
Assistant(s) -
Course Objectives This course provides review of the state of the art in deep learning and neural networks. Both theoretical aspects of deep neural network structures and algorithms as well as practical applications originating from theory will be discussed.
Learning Outcomes The students who succeeded in this course;
  • Describe deep neural networks and models.
  • Use general architectures and algorithms from deep neural networks.
  • Compare different deep learning algorithms.
  • Apply various deep neural network algorithms to specific problems.
  • Develop deep neural network models and algorithms using computer toolboxes.
Course Description The following topics will be included: feed-forward neural networks, back-propagation, convolutional neural networks, recurrent neural networks, recursive neural networks, regularization, optimization.
Related Sustainable Development Goals

 



Course Category

 Core Courses
Major Area Courses
Supportive Courses
Media and Managment Skills Courses
Transferable Skill Courses

 

WEEKLY SUBJECTS AND RELATED PREPARATION STUDIES

Week Subjects Required Materials
1 Introduction Chapter 1. Deep Learning. I. Goodfellow, Y. Bengio, A. Courville. ISBN: 9780262035613.
2 Applied Math and Machine Learning Basics Chapter 2-3. Deep Learning. I. Goodfellow, Y. Bengio, A. Courville. ISBN: 9780262035613.
3 Applied Math and Machine Learning Basics Chapter 4-5. Deep Learning. I. Goodfellow, Y. Bengio, A. Courville. ISBN: 9780262035613.
4 Deep Feedforward Networks Chapter 6. Deep Learning. I. Goodfellow, Y. Bengio, A. Courville. ISBN: 9780262035613.
5 Regularization for Deep Learning Chapter 7. Deep Learning. I. Goodfellow, Y. Bengio, A. Courville. ISBN: 9780262035613.
6 Regularization for Deep Learning Chapter 7. Deep Learning. I. Goodfellow, Y. Bengio, A. Courville. ISBN: 9780262035613.
7 Optimization for Deep Models Chapter 8. Deep Learning. I. Goodfellow, Y. Bengio, A. Courville. ISBN: 9780262035613.
8 Optimization for Deep Models Chapter 8. Deep Learning. I. Goodfellow, Y. Bengio, A. Courville. ISBN: 9780262035613.
9 Midterm Exam
10 Convolutional Networks Chapter 9. Deep Learning. I. Goodfellow, Y. Bengio, A. Courville. ISBN: 9780262035613.
11 Convolutional Networks Chapter 9. Deep Learning. I. Goodfellow, Y. Bengio, A. Courville. ISBN: 9780262035613.
12 Recurrent and Recursive Nets Chapter 10 Deep Learning. I. Goodfellow, Y. Bengio, A. Courville. ISBN: 9780262035613.
13 Recurrent and Recursive Nets Chapter 10 Deep Learning. I. Goodfellow, Y. Bengio, A. Courville. ISBN: 9780262035613.
14 Practical Methodology and Applications Chapter 11-12. Deep Learning. I. Goodfellow, Y. Bengio, A. Courville. ISBN: 9780262035613.
15 Deep Generative Models Chapter 20. Deep Learning. I. Goodfellow, Y. Bengio, A. Courville. ISBN: 9780262035613.
16 General review of semester
Course Notes/Textbooks

I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press, 2016, ISBN: 9780262035613
Suggested Readings/Materials

 

EVALUATION SYSTEM

Semester Activities Number Weigthing
Participation
Laboratory / Application
Field Work
Quizzes / Studio Critiques
4
30
Portfolio
Homework / Assignments
Presentation / Jury
Project
Seminar / Workshop
Oral Exam
Midterm
1
30
Final Exam
1
40
Total

Weighting of Semester Activities on the Final Grade
5
60
Weighting of End-of-Semester Activities on the Final Grade
1
40
Total

ECTS / WORKLOAD TABLE

Semester Activities Number Duration (Hours) Workload
Course Hours
(Including exam week: 16 x total hours)
16
3
48
Laboratory / Application Hours
(Including exam week: 16 x total hours)
16
Study Hours Out of Class
15
3
45
Field Work
Quizzes / Studio Critiques
4
5
Portfolio
Homework / Assignments
Presentation / Jury
Project
Seminar / Workshop
Oral Exam
Midterms
1
15
Final Exams
1
22
    Total
150

 

COURSE LEARNING OUTCOMES AND PROGRAM QUALIFICATIONS RELATIONSHIP

#
 Program Competencies/Outcomes
* Contribution Level
1
2
3
4
5
1

To have adequate knowledge in Mathematics, Science, Computer Science and Software Engineering; to be able to use theoretical and applied information in these areas on complex engineering problems.

 X
2

To be able to identify, define, formulate, and solve complex Software Engineering problems; to be able to select and apply proper analysis and modeling methods for this purpose.

 X
3

To be able to design, implement, verify, validate, document, measure and maintain a complex software system, process, or product under realistic constraints and conditions, in such a way as to meet the requirements; ability to apply modern methods for this purpose.

 X
4

To be able to devise, select, and use modern techniques and tools needed for analysis and solution of complex problems in software engineering applications; to be able to use information technologies effectively.

 X
5

To be able to design and conduct experiments, gather data, analyze and interpret results for investigating complex Software Engineering problems.

 X
6

To be able to work effectively in Software Engineering disciplinary and multi-disciplinary teams; to be able to work individually.
7

To be able to communicate effectively in Turkish, both orally and in writing; to be able to author and comprehend written reports, to be able to prepare design and implementation reports, to be able to present effectively, to be able to give and receive clear and comprehensible instructions.
8

To have knowledge about global and social impact of engineering practices and software applications on health, environment, and safety; to have knowledge about contemporary issues as they pertain to engineering; to be aware of the legal ramifications of Engineering and Software Engineering solutions.
9

To be aware of ethical behavior, professional and ethical responsibility; to have knowledge about standards utilized in engineering applications.
10

To have knowledge about industrial practices such as project management, risk management, and change management; to have awareness of entrepreneurship and innovation; to have knowledge about sustainable development.
11

To be able to collect data in the area of Software Engineering, and to be able to communicate with colleagues in a foreign language. ("European Language Portfolio Global Scale", Level B1)
12

To be able to speak a second foreign language at a medium level of fluency efficiently.
13

To recognize the need for lifelong learning; to be able to access information, to be able to stay current with developments in science and technology; to be able to relate the knowledge accumulated throughout the human history to Software Engineering.

*1 Lowest, 2 Low, 3 Average, 4 High, 5 Highest