COMPUTER ENGINEERING
Bachelor	TR-NQF-HE: Level 6	QF-EHEA: First Cycle	EQF-LLL: Level 6

Ders Genel Tanıtım Bilgileri

Course Code:

1410002003

Ders İsmi:

Deep Learning

Ders Yarıyılı:

Fall

Ders Kredileri:

Theoretical	Practical	Credit	ECTS
3	0	3	5

Language of instruction:

Ders Koşulu:

Ders İş Deneyimini Gerektiriyor mu?:

Type of course:

Bölüm Seçmeli

Course Level:

Bachelor

TR-NQF-HE:6. Master`s Degree

QF-EHEA:First Cycle

EQF-LLL:6. Master`s Degree

Mode of Delivery:

Face to face

Course Coordinator :

Dr.Öğr.Üyesi Recep DURANAY

Course Lecturer(s):

Prof. Dr. Haluk GÜMÜŞKAYA

Course Assistants:

Dersin Amaç ve İçeriği

Course Objectives:

Presenting methods that can be used to learn high-level features obtained from different types of data by utilizing deep architectures and showing how these methods can be applied for different purposes from image recognition to robot control.

Course Content:

History and theoretical advantages of deep learning, Basic neural network architectures and learning algorithms that can be used for deep learning, Arrangement of Distributed Models, Optimization Techniques for Training Deep Models, Convolutional networks, Feedback and recursive networks, Autoencoders and Linear Factor Models, Learning by Representation, Deep Productive Models – Boltzman Machines.

Learning Outcomes

The students who have succeeded in this course;

Learning Outcomes

1 - Knowledge
Theoretical - Conceptual
1) Students can evaluate common deep learning methods in terms of effectiveness.
2 - Skills
Cognitive - Practical
1) Students can evaluate the advantages and disadvantages of the deep learning method that is planned to be used.
2) Students can design and test basic deep learning solutions.
3 - Competences
Communication and Social Competence
Learning Competence
1) Students identify and apply the appropriate deep learning architecture and algorithm for the predicted solution.
Field Specific Competence
Competence to Work Independently and Take Responsibility
1) Students are familiar with editing and optimization methods of deep models.

Ders Akış Planı

Week	Subject	Related Preparation
1)	Introduction – History and Theoretical Foundations
2)	Mathematical Fundamentals: Linear Algebra, Probability and Information Theory lesson
3)	Artificial Neural Networks Fundamentals
4)	Feed Forward Deep Networks
5)	Editing Deep or Distributed Models
6)	Optimization Techniques for Training Deep Models
7)	Convolutional Networks
8)	Midterm
9)	Autoencoders and Linear Factor Models
10)	Autoencoders and Linear Factor Models	Course Book
11)	Learning through Representation
12)	Learning through Representation
13)	Deep Productive Models
14)	Deep Productive Models	Course Book
15)	Boltzman Machines
16)	Final

Sources

Course Notes / Textbooks:	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press,http://www.iro.umontreal.ca/~bengioy/dlbook, 2015.
References:	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press,http://www.iro.umontreal.ca/~bengioy/dlbook, 2015.

Ders - Program Öğrenme Kazanım İlişkisi

Ders Öğrenme Kazanımları	1	2	3	4	5
Program Outcomes
1) PO 1.1) Sufficient knowledge in mathematics, science and computer engineering
2) PO 1.2) Ability to apply theoretical and applied knowledge in mathematics, science and computer engineering for modeling and solving engineering problems.
3) PO 2.1) Identifying complex engineering problems
4) PO 2.2) Defining complex engineering problems
5) PO 2.3) Formulating complex engineering problems
6) PO 2.4) Ability to solve complex engineering problems
7) PO 2.5) Ability to choose and apply appropriate analysis and modeling methods
8) PO 3.1) Ability to design a complex system, process, device or product to meet specific requirements under realistic constraints and conditions.
9) PO 3.2) Ability to apply modern design methods under realistic constraints and conditions for a complex system, process, device or product
10) PO 4.1) Developing modern techniques and tools necessary for the analysis and solution of complex problems encountered in engineering applications
11) PO 4.2) Ability to select and use modern techniques and tools necessary for the analysis and solution of complex problems encountered in engineering applications
12) PO 4.3) Ability to use information technologies effectively.
13) PO 5.1) Examination of complex engineering problems or discipline-specific research topics, designing experiments
14) PO 5.2) Examination of complex engineering problems or discipline-specific research topics, experimentation
15) PO 5.3 ) Analysis of complex engineering problems or discipline-specific research topics, data collection
16) PO 5.4) Analyzing the results of complex engineering problems or discipline-specific research topics
17) PO 5.5) Examining and interpreting complex engineering problems or discipline-specific research topics

Ders - Öğrenme Kazanımı İlişkisi

No Effect	1 Lowest	2 Low	3 Average	4 High	5 Highest

	Program Outcomes	Level of Contribution
1)	PO 1.1) Sufficient knowledge in mathematics, science and computer engineering
2)	PO 1.2) Ability to apply theoretical and applied knowledge in mathematics, science and computer engineering for modeling and solving engineering problems.
3)	PO 2.1) Identifying complex engineering problems
4)	PO 2.2) Defining complex engineering problems
5)	PO 2.3) Formulating complex engineering problems
6)	PO 2.4) Ability to solve complex engineering problems
7)	PO 2.5) Ability to choose and apply appropriate analysis and modeling methods
8)	PO 3.1) Ability to design a complex system, process, device or product to meet specific requirements under realistic constraints and conditions.
9)	PO 3.2) Ability to apply modern design methods under realistic constraints and conditions for a complex system, process, device or product
10)	PO 4.1) Developing modern techniques and tools necessary for the analysis and solution of complex problems encountered in engineering applications
11)	PO 4.2) Ability to select and use modern techniques and tools necessary for the analysis and solution of complex problems encountered in engineering applications
12)	PO 4.3) Ability to use information technologies effectively.	5
13)	PO 5.1) Examination of complex engineering problems or discipline-specific research topics, designing experiments
14)	PO 5.2) Examination of complex engineering problems or discipline-specific research topics, experimentation
15)	PO 5.3 ) Analysis of complex engineering problems or discipline-specific research topics, data collection
16)	PO 5.4) Analyzing the results of complex engineering problems or discipline-specific research topics
17)	PO 5.5) Examining and interpreting complex engineering problems or discipline-specific research topics

Öğrenme Etkinliği ve Öğretme Yöntemleri

Course
Homework

Ölçme ve Değerlendirme Yöntemleri ve Kriterleri

Yazılı Sınav (Açık uçlu sorular, çoktan seçmeli, doğru yanlış, eşleştirme, boşluk doldurma, sıralama)
Bireysel Proje
Sunum

Assessment & Grading

Semester Requirements	Number of Activities	Level of Contribution
total		%
PERCENTAGE OF SEMESTER WORK		% 0
PERCENTAGE OF FINAL WORK		%
total		%

İş Yükü ve AKTS Kredisi Hesaplaması

Activities	Number of Activities	Duration (Hours)	Workload
Course Hours	13	3	39
Study Hours Out of Class	13	2	26
Presentations / Seminar	1	18	18
Project	1	40	40
Homework Assignments	4	9	36
Midterms	1	30	30
Final	1	30	30
Total Workload			219