|
ELI5320 | Neural Fuzzy Systems | 3+0+0 | ECTS:7.5 | Year / Semester | Fall Semester | Level of Course | Second Cycle | Status | Elective | Department | DEPARTMENT of ELECTRICAL and ELECTRONICS ENGINEERING | Prerequisites and co-requisites | None | Mode of Delivery | Face to face, Group study | Contact Hours | 14 weeks - 3 hours of lectures per week | Lecturer | Prof. Dr. İsmail Hakkı ALTAŞ | Co-Lecturer | None | Language of instruction | | Professional practise ( internship ) | None | | The aim of the course: | To give a basic understanding of Fuzzy Logic, Neural Networks, and Neural-Fuzzy Systems. |
Programme Outcomes | CTPO | TOA | Upon successful completion of the course, the students will be able to : | | | PO - 1 : | Get a review of fuzzy set theory. | 3,4,5,6 | 1,3,6 | PO - 2 : | Learn fuzzy logic and fuzzy decision making. | 3,4,5,6 | 1,3,6 | PO - 3 : | Learn fuzzy relations. | 3,4,5,7 | 1,3,6 | PO - 4 : | Learn approximate reasoning and fuzzy rule based systems. | 3,4,5,6 | 1,3,6 | PO - 5 : | Get information about Artificial Neural Networks. | 3,4,5,7 | 1,3,6 | PO - 6 : | Learn Supervised and Unsupervised Learning in Neural Networks. | 3,4,5,6 | 1,3,6 | PO - 7 : | Learn Neuro-Fuzzy Modeling. Neuro-Fuzzy Control. | 3,4,5,6 | 1,3,6 | PO - 8 : | Get familiar with the advanced Applications. | 3,4,5,7 | 1,3,6 | CTPO : Contribution to programme outcomes, TOA :Type of assessment (1: written exam, 2: Oral exam, 3: Homework assignment, 4: Laboratory exercise/exam, 5: Seminar / presentation, 6: Term paper), PO : Learning Outcome | |
A review of fuzzy set theory, fuzzy logic, fuzzy decision making, approximate reasoning, fuzzy relations, and fuzzy rule based systems. Adaptive Neural Networks. Supervised Learning Neural Networks. Learning from Reinforcement. Unsupervised Learning and Other Neural Networks. Neuro-Fuzzy Modeling. Neuro-Fuzzy Control. Advanced Applications |
|
Course Syllabus | Week | Subject | Related Notes / Files | Week 1 | A review of fuzzy set theory, | | Week 2 | fuzzy logic | | Week 3 | fuzzy decision making | | Week 4 | approximate reasoning | | Week 5 | fuzzy relations | | Week 6 | fuzzy rule based systems. | | Week 7 | Adaptive Neural Networks. | | Week 8 | Supervised Learning Neural Networks.Mid-term exam | | Week 9 | Mid-term exam. | | Week 10 | Learning from Reinforcement. | | Week 11 | Unsupervised Learning | | Week 12 | Other Neural Networks. | | Week 13 | Neuro-Fuzzy Modeling. | | Week 14 | Neuro-Fuzzy Control. | | Week 15 | Neuro-Fuzzy Control | | Week 16 | End-of-term exam | | |
1 | Altaş, İ. H., Lecture Notes, Unpublished. | | |
1 | Jang, J.S.R., Sun, C.T., and Mizutani, E.,1996; Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, Prentice Hall, | | 2 | Nauck, D., Klawonn, F., Kruse, R., 1997; Foundations on Neuro-Fuzzy Systems, Wiley, Chichester, | | 3 | Klir, G.J. and Folger, T.A., Fuzzy Sets, Uncertainity, and Information, Prentice Hall, Inc. | | 4 | Lin, 1996; Neural Fuzzy Systems: A Neuro-Fuzzy Synergism., Prentice Hall. | | 5 | Ross, T.J., 1995; Fuzzy Logic with Engineering Applications, McGraw-Hill Book Company, . | | |
Method of Assessment | Type of assessment | Week No | Date | Duration (hours) | Weight (%) | Mid-term exam | 9 | | 2 | 30 | Project | 14 | | 10 | 20 | End-of-term exam | 16 | | 2 | 50 | |
Student Work Load and its Distribution | Type of work | Duration (hours pw) | No of weeks / Number of activity | Hours in total per term | Yüz yüze eğitim | 3 | 14 | 42 | Sınıf dışı çalışma | 4 | 10 | 40 | Laboratuar çalışması | 0 | 0 | 0 | Arasınav için hazırlık | 2 | 7 | 14 | Arasınav | 2 | 1 | 2 | Uygulama | 0 | 0 | 0 | Klinik Uygulama | 0 | 0 | 0 | Ödev | 2 | 13 | 26 | Proje | 5 | 13 | 65 | Kısa sınav | 0 | 0 | 0 | Dönem sonu sınavı için hazırlık | 2 | 14 | 28 | Dönem sonu sınavı | 2 | 1 | 2 | Diğer 1 | 0 | 0 | 0 | Diğer 2 | 0 | 0 | 0 | Total work load | | | 219 |
|