Nevşehir Hacı Bektaş Veli University Course Catalogue

Information Of Programmes

INSTITUTE OF SCIENCE / EEM-617 - ELEKTRIK-ELEKTRONIK MüHENDISLIğI ANABILIM DALı DOKTORA (ÖNERILEN PROGRAM)

Code: EEM-617 Course Title: MODELING OF ARTIFICIAL NEURAL NETWORKS Theoretical+Practice: 3+0 ECTS: 6
Year/Semester of Study 1 / Fall Semester
Level of Course 3rd Cycle Degree Programme
Type of Course Optional
Department ELEKTRIK-ELEKTRONIK MüHENDISLIğI ANABILIM DALı DOKTORA (ÖNERILEN PROGRAM)
Pre-requisities and Co-requisites None
Mode of Delivery Face to Face
Teaching Period 14 Weeks
Name of Lecturer UĞUR SORGUCU (sorgucu@nevsehir.edu.tr)
Name of Lecturer(s)
Language of Instruction Turkish
Work Placement(s) None
Objectives of the Course
To teach the concepts that make up the structure of artificial neural networks, To teach learning algorithms used in artificial neural networks, To teach the applications of artificial neural networks in engineering and other branches, To teach how to solve real problems on computer programmes with artificial neural networks

Learning Outcomes PO MME
The students who succeeded in this course:
LO-1 PO-1 Conducting scientific research on subjects specific to the Electrical and Electronics Engineering discipline, interpreting this information and gaining application skills.
PO-2 Ability to develop, select and use modern techniques and tools required for the analysis and solution of complex problems encountered in engineering applications; has the ability to use information technologies effectively.
Examination
Term Paper
PO: Programme Outcomes
MME:Method of measurement & Evaluation

Course Contents
1- Information about the structure of the brain, biological networks and nervous system 2- Artificial neural systems: Neural computation, development history of ANNs. Basic concepts and models of ANNs - 1 3- Artificial neural systems: Neural computation, development history of ANNs. Basic concepts and models of ANNs - 2 4- ANN models, neural processing. 5- Learning and adaptation, neural network learning rules - 1 6- Learning and adaptation, neuro learning rules - 2 7- Single-layer neural classifiers 8- Visa 9- Single-layer feedback networks 10- Multilayer feed-forward networks - 1 11- Multilayer feed-forward networks - 2 12- Applications of neural algorithms and systems. Implementation of neural networks - 1 13- Applications of neural algorithms and systems. Implementation of neural networks - 2 14- Matlab applications
Weekly Course Content
Week Subject Learning Activities and Teaching Methods
1 Information about the structure of the brain, biological networks and nervous system
2 Artificial neural systems: Neural computation, development history of ANNs. Basic concepts and models of ANNs - 1 Lecture, question-answer, discussion ( e-learning)
3 Artificial neural systems: Neural computation, development history of ANNs. Basic concepts and models of ANNs - 2 Lecture, question-answer, discussion ( e-learning)
4 ANN models, neural processing. Lecture, question-answer, discussion ( e-learning)
5 Learning and adaptation, neural network learning rules - 1 Lecture, question-answer, discussion ( e-learning)
6 Learning and adaptation, neuro learning rules - 2 Lecture, question-answer, discussion ( e-learning)
7 Single-layer neural classifiers Lecture, question-answer, discussion ( e-learning)
8 mid-term exam
9 Single-layer feedback networks Lecture, question-answer, discussion ( e-learning)
10 Multilayer feed-forward networks - 1 Lecture, question-answer, discussion ( e-learning)
11 Multilayer feed-forward networks - 2 Lecture, question-answer, discussion ( e-learning)
12 Applications of neural algorithms and systems. Implementation of neural networks - 1 Lecture, question-answer, discussion ( e-learning)
13 Applications of neural algorithms and systems. Implementation of neural networks - 2 Lecture, question-answer, discussion ( e-learning)
14 Matlab applications Lecture, question-answer, discussion ( e-learning)
15 Matlab applications Lecture, question-answer, discussion ( e-learning)
16 final exam
Recommend Course Book / Supplementary Book/Reading
1 Prof. Dr. Çetin ELMAS, Yapay Zeka Uygulamaları, SEÇKİN YAYINCILIK
2 S. Haykin. "Neural Networks: A Comprehensive Foundation", (2nd ed.), Prentice Hall PTR, Upper Saddle River, NJ, USA, 2008.
3 E. Öztemel, "Yapay Sinir Ağları", Papatya Yayıncılık, 2008.
Required Course instruments and materials
Coursebook, Laptop computer

Assessment Methods
Type of Assessment Week Hours Weight(%)
mid-term exam 8 2 40
Other assessment methods
1.Oral Examination
2.Quiz
3.Laboratory exam
4.Presentation
5.Report
6.Workshop
7.Performance Project
8.Term Paper
9.Project
final exam 16 2 60

Student Work Load
Type of Work Weekly Hours Number of Weeks Work Load
Weekly Course Hours (Theoretical+Practice) 3 14 42
Outside Class
       a) Reading 3 10 30
       b) Search in internet/Library 3 10 30
       c) Performance Project 0
       d) Prepare a workshop/Presentation/Report 0
       e) Term paper/Project 0
Oral Examination 0
Quiz 0
Laboratory exam 0
Own study for mid-term exam 4 9 36
mid-term exam 3 1 3
Own study for final exam 4 9 36
final exam 3 1 3
0
0
Total work load; 180