| Semester | Course Unit Code | Course Unit Title | T+P+L | Credit | Number of ECTS Credits |
| 1 | EEE506 | AN INTRODUCTION TO NEURAL NETWORKS | 3+0+0 | 3 | 6 |
|
Language of Instruction
|
English
|
|
Level of Course Unit
|
Master's Degree
|
|
Department / Program
|
ELECTRICAL AND ELECTRONICS ENGINEERING
|
|
Mode of Delivery
|
Face to Face
|
|
Type of Course Unit
|
Elective
|
|
Objectives of the Course
|
Introducing the main fundamental principles and techniques of neural network systems. Investigating the principal neural network models and applications.
|
|
Course Content
|
Principals of neural computing. Architectural analysis of different neural network models (Hopfield Model, single perceptron, multilayer perceptron etc.). Learning algorithms, backpropagation algorithm and local minima problem. Dynamics of recurrent neural networks. Applications of neural networks for control systems, system identification, associative memories, optimiztion problems etc.
|
|
Course Methods and Techniques
|
|
|
Prerequisites and co-requisities
|
None
|
|
Course Coordinator
|
None
|
|
Name of Lecturers
|
Asist Prof. Serkan ÖZBAY
|
|
Assistants
|
None
|
|
Work Placement(s)
|
No
|
Recommended or Required Reading
|
Resources
|
Fundamentals of Neural Networks Architectures, Algorithms, and Applications Laurene Fausett
|
|
|
Neural Network Design (Second Edition)
Martin T. Hagan
Howard B. Demuth
Mark Hudson Beale
Orlando De Jesús
|
|
|
|
|
|
|
|
|
|
Course Category
|
Mathematics and Basic Sciences
|
%30
|
|
|
Engineering
|
%30
|
|
|
Engineering Design
|
%40
|
|
|
Social Sciences
|
%0
|
|
|
Education
|
%0
|
|
|
Science
|
%0
|
|
|
Health
|
%0
|
|
|
Field
|
%0
|
|
|
Planned Learning Activities and Teaching Methods
Activities are given in detail in the section of "Assessment Methods and Criteria" and "Workload Calculation"
Assessment Methods and Criteria
|
In-Term Studies
|
|
Mid-terms
|
2
|
%
60
|
|
Final examination
|
1
|
%
40
|
|
Total
|
3
|
%
100
|
ECTS Allocated Based on Student Workload
|
Activities
|
Total Work Load
|
|
Course Duration
|
14
|
3
|
42
|
|
Hours for off-the-c.r.stud
|
14
|
4
|
56
|
|
Mid-terms
|
2
|
32
|
64
|
|
Final examination
|
1
|
20
|
20
|
|
Total Work Load
| |
|
Number of ECTS Credits 6
182
|
Course Learning Outcomes: Upon the successful completion of this course, students will be able to:
| No | Learning Outcomes |
|
1
| Describing the relation between real brains and simple artificial neural network models |
|
2
| Explaining the most common architectures and learning algorithms in neural networks |
|
3
| Discussing the main factors involved in achieving good learning and generalization performance in neural network systems |
|
4
| Evaluating the practical considerations in neural network applications |
Weekly Detailed Course Contents
| Week | Topics | Study Materials | Materials |
| 1 |
Principals of neural computing
|
|
|
| 2 |
Neuron model and network architectures
|
|
|
| 3 |
Neuron model and network architectures
|
|
|
| 4 |
Architectural analysis of different neural network models: Feedforward (Perceptron) model
|
|
|
| 5 |
Recurrent (Hopfield) model, Competitive (Hamming) model
|
|
|
| 6 |
Learning algorithms:Supervised and unsupervised learning
|
|
|
| 7 |
Hebb learning rule
|
|
|
| 8 |
Perceptron learning rule
|
|
|
| 9 |
LMS algorithm
|
|
|
| 10 |
Performance learning
|
|
|
| 11 |
Backpropagation algorithm
|
|
|
| 12 |
Backpropagation algorithm
|
|
|
| 13 |
Dynamics of recurrent neural networks
|
|
|
| 14 |
Dynamics of recurrent neural networks
|
|
|
Contribution of Learning Outcomes to Programme Outcomes
bbb
https://obs.gantep.edu.tr/oibs/bologna/progCourseDetails.aspx?curCourse=147925&lang=en