GRADUATE SCHOOL
M.SC. In Industrial Engineering (With Thesis)
EEE 511 | Course Introduction and Application Information
Course Name |
Artificial Neural Networks for Signal Processing and Control
|
Code
|
Semester
|
Theory
(hour/week) |
Application/Lab
(hour/week) |
Local Credits
|
ECTS
|
EEE 511
|
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 | - | |||||
Course Coordinator | ||||||
Course Lecturer(s) | ||||||
Assistant(s) | - |
Course Objectives | The course aims the students: i) to know basic artificial neural networks models and learning algorithms and ii) to use artificial neural networks models and associated learning algorithms for signal processing and control applications. |
Learning Outcomes |
The students who succeeded in this course;
|
Course Description | Artificial neural networks architectures and learning algorithms. Multi layer perceptron, radial basis function networks and support vector machines. Regression / function approximation, classification and clustering. Artificial neural networks for signal processing, filtering and pattern recognition. Artificial neural networks for system identification and control. |
|
Core Courses | |
Major Area Courses | ||
Supportive Courses | ||
Media and Management Skills Courses | ||
Transferable Skill Courses |
WEEKLY SUBJECTS AND RELATED PREPARATION STUDIES
Week | Subjects | Related Preparation |
1 | Biological motivation. Historical remarks. | Introduction. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes. |
2 | Taxonomy of artificial neural networks and learning algorithms. | Introduction. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes. |
3 | Linear adaptive element, least mean square algorithm and convergence analysis. | Introduction. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes. |
4 | Discrete perceptron, perceptron learning rule and convergence analysis | Introduction. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes. |
5 | Multi-layer perceptron, back propagation algorithm and its variants with their convergence analyses, overfitting. | Introduction. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes. |
6 | Radial basis function networks, design by input and input-output clustering | Introduction. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes. |
7 | Support vector machines, Mercer theorem, kernel representation, Lagrange multipliers | Introduction. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes. |
8 | Generalization,Vapnik-Chervonenkis dimension. | Introduction. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes. |
9 | 1. Midterm | |
10 | Pattern recognition, feature extraction, dimension and data reduction by artificial neural networks. | Introduction. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes. |
11 | 1-Dimensional biomedical signal processing by artificial neural networks. | Introduction. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes. |
12 | Biomedical image processing by artificial neural networks | Introduction. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes. |
13 | 2. Midterm | |
14 | Systems identification by artificial neural networks. | Introduction. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes. |
15 | Artificial neural networks based controller design. | Introduction. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes., |
16 | Review of the Semester |
Course Notes/Textbooks | The textbook referenced above and lecture notes |
Suggested Readings/Materials | Related Books and Research Papers |
EVALUATION SYSTEM
Semester Activities | Number | Weigthing |
Participation | ||
Laboratory / Application |
6
|
60
|
Field Work | ||
Quizzes / Studio Critiques | ||
Portfolio | ||
Homework / Assignments | ||
Presentation / Jury | ||
Project |
2
|
40
|
Seminar / Workshop | ||
Oral Exams | ||
Midterm | ||
Final Exam | ||
Total |
Weighting of Semester Activities on the Final Grade |
8
|
100
|
Weighting of End-of-Semester Activities on the Final Grade | ||
Total |
ECTS / WORKLOAD TABLE
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
|
2
|
32
|
Study Hours Out of Class |
15
|
4
|
60
|
Field Work |
0
|
||
Quizzes / Studio Critiques |
0
|
||
Portfolio |
0
|
||
Homework / Assignments |
0
|
||
Presentation / Jury |
0
|
||
Project |
2
|
42
|
84
|
Seminar / Workshop |
0
|
||
Oral Exam |
0
|
||
Midterms |
0
|
||
Final Exam |
0
|
||
Total |
224
|
COURSE LEARNING OUTCOMES AND PROGRAM QUALIFICATIONS RELATIONSHIP
#
|
Program Competencies/Outcomes |
* Contribution Level
|
||||
1
|
2
|
3
|
4
|
5
|
||
1 | To have an appropriate knowledge of methodological and practical elements of the basic sciences and to be able to apply this knowledge in order to describe engineering-related problems in the context of industrial systems. |
|||||
2 | To be able to identify, formulate and solve Industrial Engineering-related problems by using state-of-the-art methods, techniques and equipment. |
|||||
3 | To be able to use techniques and tools for analyzing and designing industrial systems with a commitment to quality. |
|||||
4 | To be able to conduct basic research and write and publish articles in related conferences and journals. |
|||||
5 | To be able to carry out tests to measure the performance of industrial systems, analyze and interpret the subsequent results. |
|||||
6 | To be able to manage decision-making processes in industrial systems. |
|||||
7 | To have an aptitude for life-long learning; to be aware of new and upcoming applications in the field and to be able to learn them whenever necessary. |
|||||
8 | To have the scientific and ethical values within the society in the collection, interpretation, dissemination, containment and use of the necessary technologies related to Industrial Engineering. |
|||||
9 | To be able to design and implement studies based on theory, experiments and modeling; to be able to analyze and resolve the complex problems that arise in this process; to be able to prepare an original thesis that comply with Industrial Engineering criteria. |
|||||
10 | To be able to follow information about Industrial Engineering in a foreign language; to be able to present the process and the results of his/her studies in national and international venues systematically, clearly and in written or oral form. |
*1 Lowest, 2 Low, 3 Average, 4 High, 5 Highest