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

Course Introduction and Application Information

Course Code	Course Name	Semester	Theoretical	Practical	Credit	ECTS
SEN4107	Introduction to Neural Networks	Fall	3	0	3	6

This catalog is for information purposes. Course status is determined by the relevant department at the beginning of semester.

Basic information

Language of instruction:	English
Type of course:	Departmental Elective
Course Level:	Bachelor’s Degree (First Cycle)
Mode of Delivery:	Hybrid
Course Coordinator :	Dr. Öğr. Üyesi AYLA GÜLCÜ
Course Objectives:	Understanding the mathematical foundations of deep learning, learning basic neural network structures like feed-forward, convolutional and recurrent neural networks; examining the application areas of different networks and using these structures for solving real life problems. Recognition of reinforcement learning techniques.

Learning Outcomes

The students who have succeeded in this course;
Understands the mathematics of deep neural networks
Demonstrates the ability to design, build and train deep feed-forward neural networks using PyTorch
Demonstrates the ability to design, build and train convolutional neural networks using PyTorch
Learns object recognition and detection models
Demonstrates the ability to design, build and train recurrent neural networks using PyTorch
Demonstrates the ability to build, train and fine tune neural network models for the real world problems
Learns reinforcement learning techniques

Course Content

Deep feed-forward neural networks, Pytorch deep learning framework, convolutional neural networks, object recognition and object detection problems, recurrent neural networks, attention mechanism, deep generative models and reinforcement learning.

Weekly Detailed Course Contents

Week	Subject	Related Preparation
1)	Introduction to Deep Learning
2)	Overview of machine learning, linear classifiers, loss functions
3)	Stochastic gradient descent and contemporary variants, back-propagation
4)	Feed-forward networks and training
5)	Feed-forward networks and training (PyTorch and cloud)
6)	Convolutional neural networks (CNNs)
7)	Understanding and Visualizing CNNs
8)	Midterm Exam
9)	Object Detection Approaches
10)	Recurrent neural networks
11)	Recurrent neural networks
12)	Attention and Memory
13)	Deep generative models
14)	Deep reinforcement learning
15)

Sources

Course Notes / Textbooks:	“Deep Learning by Ian Goodfellow”, Yoshua Bengio and Aaron Courville, MIT Press (2016)
References:	“Hands-On Neural Networks with PyTorch 1.0”, Vihar Kurama, Pakt Publishing (2019) https://www.deeplearningbook.org/ “Machine Learning: A Probabilistic Perspective”, K. P. Murphy, MIT Press (2012) “Pattern Recognition and Machine Learning”, C. M. Bishop, Springer (2006)

Evaluation System

Semester Requirements	Number of Activities	Level of Contribution
Quizzes	5	% 25
Project	1	% 15
Midterms	1	% 20
Final	1	% 40
Total		% 100
PERCENTAGE OF SEMESTER WORK		% 45
PERCENTAGE OF FINAL WORK		% 55
Total		% 100

ECTS / Workload Table

Activities	Number of Activities	Duration (Hours)	Workload
Course Hours	13	3	39
Study Hours Out of Class	13	8	104
Project	1	3	3
Quizzes	5	1	5
Midterms	1	2	2
Final	1	2	2
Total Workload			155

Contribution of Learning Outcomes to Programme Outcomes

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

	Program Outcomes	Level of Contribution
1)	Be able to specify functional and non-functional attributes of software projects, processes and products.
2)	Be able to design software architecture, components, interfaces and subcomponents of a system for complex engineering problems.
3)	Be able to develop a complex software system with in terms of code development, verification, testing and debugging.
4)	Be able to verify software by testing its program behavior through expected results for a complex engineering problem.
5)	Be able to maintain a complex software system due to working environment changes, new user demands and software errors that occur during operation.
6)	Be able to monitor and control changes in the complex software system, to integrate the software with other systems, and to plan and manage new releases systematically.
7)	Be able to identify, evaluate, measure, manage and apply complex software system life cycle processes in software development by working within and interdisciplinary teams.
8)	Be able to use various tools and methods to collect software requirements, design, develop, test and maintain software under realistic constraints and conditions in complex engineering problems.
9)	Be able to define basic quality metrics, apply software life cycle processes, measure software quality, identify quality model characteristics, apply standards and be able to use them to analyze, design, develop, verify and test complex software system.
10)	Be able to gain technical information about other disciplines such as sustainable development that have common boundaries with software engineering such as mathematics, science, computer engineering, industrial engineering, systems engineering, economics, management and be able to create innovative ideas in entrepreneurship activities.
11)	Be able to grasp software engineering culture and concept of ethics and have the basic information of applying them in the software engineering and learn and successfully apply necessary technical skills through professional life.
12)	Be able to write active reports using foreign languages and Turkish, understand written reports, prepare design and production reports, make effective presentations, give clear and understandable instructions.
13)	Be able to have knowledge about the effects of engineering applications on health, environment and security in universal and societal dimensions and the problems of engineering in the era and the legal consequences of engineering solutions.