M.SC. in Electrical and Electronics Engineering (Without Thesis)

EEE 517 | Course Introduction and Application Information

Course Name

Deep Learning Methods and Applications

Code	Semester	Theory (hour/week)	Application/Lab (hour/week)	Local Credits	ECTS
EEE 517	Fall/Spring	3	0	3	7.5

Prerequisites	None
Course Language	English
Course Type	Elective
Course Level	Second / Third Cycle
Mode of Delivery	-
Teaching Methods and Techniques of the Course	Problem Solving Application: Experiment / Laboratory / Workshop Lecture / Presentation
National Occupation Classification	-
Course Coordinator	Dr. Öğr. Üyesi Ayça Kumluca Topallı
Course Lecturer(s)	Dr. Öğr. Üyesi Ayça Kumluca Topallı
Assistant(s)	-

Course Objectives

This course aims to give students a general understanding of machine learning (ML) terminology; most common deep learning (DL) algorithms; applications of DL techniques to real-life problems with Python and TensorFlow (TF), parameter selections for learning and interpretation of the results.

Learning Outcomes

#	Content	PC Sub	* Contribution Level
#	Content	PC Sub	1	2	3	4	5
1	build and train deep neural networks with TF,
2	identify main architectural parameters of DL,
3	build convolutional neural networks (CNN) and apply them for object detection with image data,
4	build and train recurrent neural networks (RNN),
5	work with natural language processing (NLP) and word embedding.

Course Description

This course is an introduction to deep learning which is behind many recent advances in AI, such as face recognition, self-driving cars, human-like speech generators, etc. A range of topics including basic neural networks, convolutional and recurrent network structures and NLP will be covered, focusing on both theory and practice. A strong mathematical background in calculus, linear algebra, probability & statistics, and coding experience with Python are expected. Machine learning background is good to have but not required.

Course Category	Core Courses
	Major Area Courses
	Supportive Courses
	Media and Management Skills Courses
	Transferable Skill Courses

WEEKLY SUBJECTS AND RELATED PREPARATION STUDIES

Week	Subjects	Related Preparation	Learning Outcome
1	Machine Learning Basics	I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press, 2016. ISBN: 978-0262035613, Ch 5.
2	Introduction to Deep Learning	I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press, 2016. ISBN: 978-0262035613, Ch 6.
3	Introduction to TensorFlow	I. Zafar et al., Hands-On Convolutional Neural Networks with TensorFlow, Packt Publishing, 2018. ISBN: 978-1789130331, Ch 1.
4	Deep Neural Networks	I. Zafar et al., Hands-On Convolutional Neural Networks with TensorFlow, Packt Publishing, 2018. ISBN: 978-1789130331, Ch 2.
5	Foundations of Convolutional Neural Networks	I. Zafar et al., Hands-On Convolutional Neural Networks with TensorFlow, Packt Publishing, 2018. ISBN: 978-1789130331, Ch 2.
6	Homework 1 Presentations
7	Image Classification with TensorFlow	I. Zafar et al., Hands-On Convolutional Neural Networks with TensorFlow, Packt Publishing, 2018. ISBN: 978-1789130331, Ch 3
8	Object Detection and Segmentation with TensorFlow	I. Zafar et al., Hands-On Convolutional Neural Networks with TensorFlow, Packt Publishing, 2018. ISBN: 978-1789130331, Ch 4.
9	Improving Deep Neural Networks	I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press, 2016. ISBN: 978-0262035613, Ch 7, 8.
10	Homework 2 Presentations
11	Recurrent Neural Networks	I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press, 2016. ISBN: 978-0262035613, Ch 10.
12	Natural Language Processing	I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press, 2016. ISBN: 978-0262035613, Ch 12.
13	Homework 3 Presentations
14	Project Presentations
15	Review of the Semester
16	Final Exam

Course Notes/Textbooks	I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press, 2016. http://www.deeplearningbook.org ISBN: 978-0262035613 I. Zafar et al., Hands-On Convolutional Neural Networks with TensorFlow, Packt Publishing, 2018. ISBN: 978-1789130331
Suggested Readings/Materials	Deep Learning Specialization https://www.coursera.org/specializations/deep-learning TensorFlow https://www.tensorflow.org

EVALUATION SYSTEM

Semester Activities	Number	Weighting	LO 1	LO 2	LO 3	LO 4	LO 5
Participation
Laboratory / Application
Field Work
Quizzes / Studio Critiques
Portfolio
Homework / Assignments	3	30
Presentation / Jury
Project	1	40
Seminar / Workshop
Oral Exams
Midterm
Final Exam	1	30
Total

Weighting of Semester Activities on the Final Grade	4	70
Weighting of End-of-Semester Activities on the Final Grade	1	30
Total

ECTS / WORKLOAD TABLE

Semester Activities	Number	Duration (Hours)	Workload
Theoretical Course Hours (Including exam week: 16 x total hours)	16	3	48
Laboratory / Application Hours (Including exam week: '.16.' x total hours)	16		0
Study Hours Out of Class	14	4	56
Field Work			0
Quizzes / Studio Critiques			0
Portfolio			0
Homework / Assignments	3	12	36
Presentation / Jury			0
Project	1	60	60
Seminar / Workshop			0
Oral Exam			0
Midterms			0
Final Exam	1	20	20
		Total	220

COURSE LEARNING OUTCOMES AND PROGRAM QUALIFICATIONS RELATIONSHIP

#	PC Sub	Program Competencies/Outcomes	* Contribution Level
#	PC Sub	Program Competencies/Outcomes	1	2	3	4	5
1	Accesses information in breadth and depth by conducting scientific research in Electrical and Electronics Engineering, evaluates, interprets and applies information.		-	-	-	-	-
2	Is well-informed about contemporary techniques and methods used in Electrical and Electronics Engineering and their limitations.		-	-	-	-	-
3	Uses scientific methods to complete and apply information from uncertain, limited or incomplete data, can combine and use information from different disciplines.		-	-	-	-	-
4	Is informed about new and upcoming applications in the field and learns them whenever necessary.		-	-	-	-	-
5	Defines and formulates problems related to Electrical and Electronics Engineering, develops methods to solve them and uses progressive methods in solutions.		-	-	-	-	-
6	Develops novel and/or original methods, designs complex systems or processes and develops progressive/alternative solutions in designs.		-	-	-	-	-
7	Designs and implements studies based on theory, experiments and modelling, analyses and resolves the complex problems that arise in this process.		-	-	-	-	-
8	Can work effectively in interdisciplinary teams as well as teams of the same discipline, can lead such teams and can develop approaches for resolving complex situations, can work independently and takes responsibility.		-	-	-	-	-
9	Engages in written and oral communication at least in Level B2 of the European Language Portfolio Global Scale.		-	-	-	-	-
10	Communicates the process and the results of his/her studies in national and international venues systematically, clearly and in written or oral form.		-	-	-	-	-
11	Is knowledgeable about the social, environmental, health, security and law implications of Electrical and Electronics engineering applications, knows their project management and business applications, and is aware of their limitations in Electrical and Electronics engineering applications.		-	-	-	-	-
12	Highly regards scientific and ethical values in data collection, interpretation, communication and in every professional activity.		-	-	-	-	-