DEPARTMENT OF SOFTWARE ENGINEERING (ENGLISH)
Bachelor	TR-NQF-HE: Level 6	QF-EHEA: First Cycle	EQF-LLL: Level 6

Ders Genel Tanıtım Bilgileri

Course Code:

1413002007

Ders İsmi:

Deep Learning

Ders Yarıyılı:

Spring

Ders Kredileri:

Theoretical	Practical	Credit	ECTS
3	0	3	5

Language of instruction:

Ders Koşulu:

Ders İş Deneyimini Gerektiriyor mu?:

Type of course:

Department Elective

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 Adem ÖZYAVAŞ

Course Lecturer(s):

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 artificial 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) Students can evaluate the advantages and disadvantages of the deep learning method that is considered to be used.
3) Students can design and test basic deep learning solutions.
4) Students identify and apply the appropriate deep learning architecture and algorithm for the predicted solution.
5) Students have knowledge about editing and optimization methods of deep models.
2 - Skills
Cognitive - Practical
3 - Competences
Communication and Social Competence
Learning Competence
Field Specific Competence
Competence to Work Independently and Take Responsibility

Ders Akış Planı

Week	Subject	Related Preparation
1)	Introduction to pattern recognition	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.
2)	Statistical classifiers	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.
3)	Fukunaga–Koontz transform	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.
4)	Fuzzy classifier	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.
5)	stochastic methods	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.
6)	Size Reduction	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.
7)	optical filters	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.
8)	midterm 1	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.
9)	Classification with optical aliasing filters	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.
10)	Optical Fourier correlation	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.
11)	Common conversion correlation	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.
12)	Adaptive co-conversion correlation	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.
13)	Pattern tracing in sequential images	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.
14)	Pattern recognition performance measures	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.
15)	Pattern recognition performance measures	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.
16)	Final	Yoshua Bengio, Ian J. Goodfellow and Aaron Courville, “ Deep Learning”, Book in preparation for MIT Press, http://www.iro.umontreal.ca/~bengioy/dlbook, 2015. Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009. Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.

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.
Yoshua Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning: Vol. 2: No. 1, pp 1-127, 2009.
Li Deng and Dong Yu, "Deep Learning: Methods and Applications", Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387, 2014.

References:

Ders - Program Öğrenme Kazanım İlişkisi

Ders Öğrenme Kazanımları	1	2	3	4	5
Program Outcomes
1) Competent knowledge of mathematics, science and technology, and computer engineering; ability to apply this knowledge to engineering solutions.
2) Skills to design and conduct experiments, collect data, analyze and interpret results.
3) Ability to design a complex system, process, device or product under realistic constraints and conditions to meet specific requirements; ability to apply modern design methods for this purpose.
4) Ability to develop, select and use modern techniques and tools required for analysis and solution of complex problems encountered in engineering practice; ability to use information technologies effectively.
5) Ability to design and conduct experiments, collect data, analyze and interpret results to investigate complex engineering problems or discipline-specific research topics.
6) Ability to work effectively in intra-disciplinary and multi-disciplinary teams; ability to work individually.
7) Ability to communicate effectively in Turkish, both orally and in writing; Knowledge of at least one foreign language; the ability to write and understand written reports effectively, to prepare design and production reports, to make effective presentations, to give and receive clear and understandable instructions.
8) Awareness of the necessity of lifelong learning; the ability to access information, to follow developments in science and technology, and to constantly renew oneself.
9) Acting in accordance with ethical principles, professional and ethical responsibility awareness; information about standards used in engineering applications.
10) Information about business life practices such as project management, risk management and change management; awareness of entrepreneurship, innovation; information about sustainable development.
11) Knowledge about the universal and social effects of engineering applications on health, environment and safety and the problems of the age reflected in the field of engineering; awareness of the legal consequences of engineering solutions.

Ders - Öğrenme Kazanımı İlişkisi

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

	Program Outcomes	Level of Contribution
1)	Competent knowledge of mathematics, science and technology, and computer engineering; ability to apply this knowledge to engineering solutions.
2)	Skills to design and conduct experiments, collect data, analyze and interpret results.
3)	Ability to design a complex system, process, device or product under realistic constraints and conditions to meet specific requirements; ability to apply modern design methods for this purpose.
4)	Ability to develop, select and use modern techniques and tools required for analysis and solution of complex problems encountered in engineering practice; ability to use information technologies effectively.
5)	Ability to design and conduct experiments, collect data, analyze and interpret results to investigate complex engineering problems or discipline-specific research topics.
6)	Ability to work effectively in intra-disciplinary and multi-disciplinary teams; ability to work individually.
7)	Ability to communicate effectively in Turkish, both orally and in writing; Knowledge of at least one foreign language; the ability to write and understand written reports effectively, to prepare design and production reports, to make effective presentations, to give and receive clear and understandable instructions.
8)	Awareness of the necessity of lifelong learning; the ability to access information, to follow developments in science and technology, and to constantly renew oneself.
9)	Acting in accordance with ethical principles, professional and ethical responsibility awareness; information about standards used in engineering applications.
10)	Information about business life practices such as project management, risk management and change management; awareness of entrepreneurship, innovation; information about sustainable development.
11)	Knowledge about the universal and social effects of engineering applications on health, environment and safety and the problems of the age reflected in the field of engineering; awareness of the legal consequences of engineering solutions.

Öğrenme Etkinliği ve Öğretme Yöntemleri

Ölçme ve Değerlendirme Yöntemleri ve Kriterleri

Assessment & Grading

Semester Requirements	Number of Activities	Level of Contribution
Homework Assignments	4	% 5
Project	1	% 30
Midterms	1	% 25
Semester Final Exam	1	% 40
total		% 100
PERCENTAGE OF SEMESTER WORK		% 60
PERCENTAGE OF FINAL WORK		% 40
total		% 100

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
Quizzes	4	9	36
Midterms	1	30	30
Final	1	30	30
Total Workload			255