IES 550 | Course Introduction and Application Information - Ph.D. In Electrical-Electronics Engineering

Course Name

Artificial Neural Networks

Code	Semester	Theory (hour/week)	Application/Lab (hour/week)	Local Credits	ECTS
IES 550	Fall/Spring	3	0	3	7.5

Prerequisites	None
Course Language	English
Course Type	Elective
Course Level	Second Cycle
Mode of Delivery	-
Teaching Methods and Techniques of the Course	-
National Occupation Classification	-
Course Coordinator	-
Course Lecturer(s)	-
Assistant(s)	-

Course Objectives

This course will introduce the fundamental principles and algorithms of Artificial Neural Network (ANN) systems. The course will cover many subjects including basic neuron model, simple perceptron, multilayer perceptron, Backpropagation learning algorithms; radialbasis function (RBF) networks; selforganizing maps (SOM) and learning vector quantization (LVQ); supportvector machines; classification techniques; pattern recognition.

Learning Outcomes

The students who succeeded in this course;

Be able to describe basic artificial neural network models and how they relate to artificial intelligence
Have an understanding of the most common ANN architectures and their learning algorithms
Understand supervised vs. unsupervised learning techniques
Be able to discuss the main factors involved in achieving good learning and generalization performance in neural network systems
Be able to evaluate the practical considerations in applying ANNs to real classification and pattern recognition problems, basic ANNs algorithms using Matlab and its Neural Network Toolbox

Course Description

The following topics will be included: The main neural network architectures and learning algorithms; Perceptrons and the LMS algorithm; Backpropagation learning; Recurrent networks; Radial basis functions; Pattern classification; Support vector machines; Kohonen’s selforganizing feature maps; Hopfield networks.

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

Week	Subjects	Related Preparation	Learning Outcome
1	Yapay sinir ağlarına giriş, motivasyon ve uygulamaları /Introduction to artificial neural nets, motivation and applications	Chapter 1. Sections 1.1. Neural Networks: Algorithms, Applications, and Programming Techniques. Freeman & Skapura. ISBN 0201513765
2	Temel sinir hücre modeli, Hebbian öğrenme kuralı, sinir ağları yapıları/Basic neuron model, Hebbian learning rule, neural network structures	Chapter 1. Sections 1.31.6. Neural Networks: A Comprehensive Foundation. Haykin. ISBN 8178083000
3	Tekkatlı perceptron, doğrusal olmayan aktivasyon fonksiyonu, Delta kuralı /Singlelayer perceptron, nonlinear activation function, Delta rule	Chapter 1. Sections 1.2. Neural Networks: Algorithms, Applications, and Programming Techniques. Freeman & Skapura. ISBN 0201513765
4	En küçükortalamalıkare (LMS) algoritması, perceptron yakınsama teoremi /The leastmeansquare (LMS) algorithm, perceptron convergence theorem	Chapter 2. Sections 2.2. Neural Networks: Algorithms, Applications, and Programming Techniques. Freeman & Skapura. ISBN 0201513765Chapter 3. Sections 3.5, 3.9. Neural Networks: A Comprehensive Foundation. Haykin. ISBN 8178083000
5	Denetimli öğrenim: çokkatlı ağlar. Backpropagation Öğrenimi /Supervised learning: multilayer networks. Backpropagation Learning	Chapter 3. Sections 3.1, 3.2. Neural Networks: Algorithms, Applications, and Programming Techniques. Freeman & Skapura. ISBN 0201513765Chapter 4. Sections 4.34.5. Neural Networks: A Comprehensive Foundation. Haykin. ISBN 8178083000
6	Ağ eğitimi ve testi için genel pratikler, çokkatlı perceptron uygulamaları /General practices for network training and testing, applications of multilayer perceptrons	Chapter 3. Sections 3.3, 3.4. Neural Networks: Algorithms, Applications, and Programming Techniques. Freeman & Skapura. ISBN 0201513765
7	Özyineli Backprop Ağları; Zaman içinde backpropagation öğrenim algoritması /Recurrent Backprop networks; Backpropagation through time learning algorithm	P.J. Werbos, “Backpropagation through time: what it does and how to do it,” Proceedings of the IEEE, 78(10), 15501560, 1990.
8	Radyaltabanlı fonksiyon (RBF) ağları ve düzenlileştirme teorisi /Radialbasis function (RBF) networks and regularization theory	Chapter 5. Sections 5.7,5.8,5.10,5.11. Neural Networks: A Comprehensive Foundation. Haykin. ISBN 8178083000
9	Çekirdek metodları, destek vektör makinesi /Kernel methods, support vector machine	Chapter 6. Sections 6.16.5. Neural Networks: A Comprehensive Foundation. Haykin. ISBN 8178083000
10	Uzmanların karışımı, EM (beklentienbüyütme) algoritması /Mixture of experts, the EM (ExpectationMaximization) algorithm	Chapter 7. Sections 7.7,7.10,7.12. Neural Networks: A Comprehensive Foundation. Haykin. ISBN 8178083000
11	Denetimsiz öğrenim, ana bileşenler analizi, rekabetçi ağlar/ Unsupervised learning, principal components analysis, competitive networks	Chapter 8. Sections 8.3. Neural Networks: A Comprehensive Foundation. Haykin. ISBN 8178083000
12	Hopfield ağları ve Boltzmann makineleri /Hopfield networks and Boltzmann machines	Chapter 4 & 5. Sections 4.14.3, 5.1,5.2. Neural Networks: Algorithms, Applications, and Programming Techniques. Freeman & Skapura. ISBN 0201513765
13	Kohonen’nin kendi kendini örgütleyen haritaları: Algoritmalar ve uygulamalar /Kohonen’s selforganizing feature maps: Algorithms and applications	Chapter 7. Sections 7.1,7.2. Neural Networks: Algorithms, Applications, and Programming Techniques. Freeman & Skapura. ISBN 0201513765
14	Bilgiteorik modeller, bağımsız bileşenler analizi /Informationtheoric models, independent components analysis	Chapter 10. Sections 10.110.3, 10.11. Neural Networks: A Comprehensive Foundation. Haykin. ISBN 8178083000
15	Örüntü tanıma için sinir ağları / Neural networks for pattern recognition	Chapter 1. Neural Networks for Pattern Recognition. Bishop. ISBN13 9780198538646
16	Review of the Semester

Course Notes/Textbooks	James A. Freeman and David M. Skapura, “Neural Networks: Algorithms, Applications, and Programming Techniques”, AddisonWesley Publishing Co., 1991, ISBN 0201513765.S. Haykin, “Neural Networks: A Comprehensive Foundation”, PrenticeHall, 2nd Ed., 1999, ISBN 8178083000.
Suggested Readings/Materials	C. M. Bishop, “Neural Networks for Pattern Recognition”, Oxford University Press, 1996, ISBN13: 9780198538646.

Semester Activities	Number	Weigthing
Participation
Laboratory / Application
Field Work
Quizzes / Studio Critiques
Portfolio
Homework / Assignments
Presentation / Jury	1*	30
Project
Seminar / Workshop
Oral Exams
Midterm	1	20
Final Exam	1	30
Total

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

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	15	6	90
Field Work			0
Quizzes / Studio Critiques			0
Portfolio			0
Homework / Assignments			0
Presentation / Jury	1*	5	5
Project			0
Seminar / Workshop			0
Oral Exam			0
Midterms	1	11	11
Final Exam	1	16	16
		Total	170

#	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. Knows and applies the research methods in studies of the area with a high level of skill.		-	-	-	-	-
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. Can independently realize novel studies that bring innovation to the field, or methods, or design, or known methods.		-	-	-	-	-
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 modeling; analyses and resolves the complex problems that arise in this process. Performs critical analysis, synthesis and evaluation of new and complex ideas.		-	-	-	-	-
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 C1 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	Evaluates the results of scientific, technological and engineering research and development activities in terms of the social, environmental, health, safety and legal aspects. Examines social relations and norms related to the field, and develops and makes attempts to change them if necessary. 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. Adheres to the principles of research and publication ethics.		-	-	-	-	-

IES 550 | Course Introduction and Application Information

WEEKLY SUBJECTS AND RELATED PREPARATION STUDIES

EVALUATION SYSTEM

ECTS / WORKLOAD TABLE

COURSE LEARNING OUTCOMES AND PROGRAM QUALIFICATIONS RELATIONSHIP

NEW GÜZELBAHÇE CAMPUS

GLOBAL CAREER

CONTRIBUTION TO SCIENCE

VALUING PEOPLE

BENEFIT TO SOCIETY