Fundamentals of Deep Learning (CMPE430) Course Detail

Course Name	Course Code	Season	Lecture Hours	Application Hours	Lab Hours	Credit	ECTS
Fundamentals of Deep Learning	CMPE430	Area Elective	2	2	0	3	5

Pre-requisite Course(s)
N/A

Course Language	English
Course Type	Elective Courses
Course Level	Bachelor’s Degree (First Cycle)
Mode of Delivery	Face To Face
Learning and Teaching Strategies	Lecture.
Course Coordinator
Course Lecturer(s)
Course Assistants
Course Objectives	The course objective is to provide an introduction to Deep Neural Network architectures, learning algorithms, and their applications.
Course Learning Outcomes	The students who succeeded in this course; Describe the concepts and techniques of Deep Neural Networks Reason about the behavior of Deep Neural Networks Evaluate which Deep Neural Network model is appropriate to a particular application Evaluate Deep Neural Network models Apply Deep Neural Networks to particular applications Identify steps to develop Deep Neural Networks
Course Content	Artificial intelligence, machine learning, and deep learning, mathematical building blocks of neural networks, binary classification, multiclass classification, regression, deep learning for computer vision.

Weekly Subjects and Releated Preparation Studies

Week	Subjects	Preparation
1	Artificial intelligence, machine learning, and deep learning	Ch. 1.1
2	Probabilistic modeling, Decision trees, Random forests, Neural networks	Ch. 1.2, Ch. 1.3
3	Data representations for neural networks	Ch. 2.1, Ch. 2.2
4	Tensor operations I	Ch. 2.3
5	Tensor operations II	Ch. 2.3
6	Gradient-based optimization I	Ch. 2.4
7	Gradient-based optimization II	Ch. 2.5
8	Deep Neural Network Model, Layers, Loss Functions	Ch. 3.1, Ch. 3.2, Ch. 3.3
9	Binary classification I	Ch. 3.4
10	Binary classification II	Ch. 3.4
11	Multiclass classification	Ch. 3.5
12	Regression	Ch. 3.6
13	Model Evaluating, Data preprocessing	Ch. 4.1, Ch. 4.2, Ch. 4.3
14	Overfitting and Underfitting, Universal workflow	Ch. 4.4, Ch. 4.5

Sources

Course Book	1. Deep Learning with Python Sep 11, 2018 by Francois Chollet , Mark Thomas , Manning Publications Co.
Other Sources	2. Deep Learning, Goodfellow, Ian, Publisher: Mit Press Place of Publication: Cambridge, Pub Year:2017
	3. Tensorflow web page, https://www.tensorflow.org
	4. Deep Learning : Fundamentals, Methods and Applications, Porter, Julius, Nova Science Publishers, Inc. 2016

Evaluation System

Requirements	Number	Percentage of Grade
Attendance/Participation	-	-
Laboratory	1	30
Application	-	-
Field Work	-	-
Special Course Internship	-	-
Quizzes/Studio Critics	-	-
Homework Assignments	1	10
Presentation	-	-
Project	-	-
Report	-	-
Seminar	-	-
Midterms Exams/Midterms Jury	1	30
Final Exam/Final Jury	1	30
Toplam	4	100

Percentage of Semester Work	70
Percentage of Final Work	30
Total	100

Course Category

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

The Relation Between Course Learning Competencies and Program Qualifications

#	Program Qualifications / Competencies	Level of Contribution
#	Program Qualifications / Competencies	1	2	3	4	5
1	Has adequate knowledge in mathematics, science, and computer engineering-specific subjects; uses theoretical and practical knowledge in these areas to solve complex engineering problems.					X
2	Identifies, defines, formulates, and solves complex engineering problems; selects and applies appropriate analysis and modeling methods for this purpose.					X
3	Designs a complex system, process, device, or product to meet specific requirements under realistic constraints and conditions; applies modern design methods for this purpose.	X
4	Develops, selects, and uses modern techniques and tools necessary for the analysis and solution of complex problems encountered in computer engineering applications; uses information technologies effectively.		X
5	Designs experiments, conducts experiments, collects data, analyzes and interprets results for the investigation of complex engineering problems or research topics specific to the discipline of computer engineering.
6	Works effectively in disciplinary and multidisciplinary teams; gains the ability to work individually.
7	Communicates effectively in Turkish, both orally and in writing; writes effective reports and understands written reports, prepares design and production reports, makes effective presentations, gives and receives clear and understandable instructions.
8	Knows at least one foreign language; writes effective reports and understands written reports, prepares design and production reports, makes effective presentations, gives and receives clear and understandable instructions.
9	Has awareness of the necessity of lifelong learning; accesses information, follows developments in science and technology, and continuously improves oneself.
10	Acts in accordance with ethical principles and has awareness of professional and ethical responsibility.
11	Has knowledge about the standards used in computer engineering applications.
12	Has knowledge about workplace practices such as project management, risk management, and change management.
13	Gains awareness about entrepreneurship and innovation.
14	Has knowledge about sustainable development.
15	Has knowledge about the health, environmental, and safety impacts of computer engineering applications in universal and societal dimensions and the contemporary issues reflected in the field of engineering.
16	Gains awareness of the legal consequences of engineering solutions.
17	Analyzes, designs, and expresses numerical computation and digital representation systems.
18	Uses programming languages and appropriate computer engineering concepts to solve computational problems.					X

ECTS/Workload Table

Activities	Number	Duration (Hours)	Total Workload
Course Hours (Including Exam Week: 16 x Total Hours)	16	2	32
Laboratory	12	2	24
Application
Special Course Internship
Field Work
Study Hours Out of Class	16	2	32
Presentation/Seminar Prepration
Project
Report
Homework Assignments	1	10	10
Quizzes/Studio Critics
Prepration of Midterm Exams/Midterm Jury	1	12	12
Prepration of Final Exams/Final Jury	1	15	15
Total Workload			125