Türkçe | English
GRADUATE INSTITUTE of NATURAL and APPLIED SCIENCES / DEPARTMENT of ELECTRICAL and ELECTRONICS ENGINEERING
Master of Science in Engineering (With Thesis)
Course Catalog
http://eee.ktu.edu.tr/eng/default_eng.aspx
Phone: +90 0462 3253154 , 3772906
FBE
GRADUATE INSTITUTE of NATURAL and APPLIED SCIENCES / DEPARTMENT of ELECTRICAL and ELECTRONICS ENGINEERING / Master of Science in Engineering (With Thesis)
Katalog Ana Sayfa
  Katalog Ana Sayfa  KTÜ Ana Sayfa   Katalog Ana Sayfa
 
 
ELI5320Neural Fuzzy Systems3+0+0ECTS:7.5
Year / SemesterFall Semester
Level of CourseSecond Cycle
Status Elective
DepartmentDEPARTMENT of ELECTRICAL and ELECTRONICS ENGINEERING
Prerequisites and co-requisitesNone
Mode of DeliveryFace to face, Group study
Contact Hours14 weeks - 3 hours of lectures per week
LecturerProf. Dr. İsmail Hakkı ALTAŞ
Co-LecturerNone
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 OutcomesCTPOTOA
Upon successful completion of the course, the students will be able to :
PO - 1 : Get a review of fuzzy set theory.3,4,5,6,7,9,101,3,6
PO - 2 : Learn fuzzy logic and fuzzy decision making.3,4,5,6,7,9,101,3,6
PO - 3 : Learn fuzzy relations.3,4,5,6,7,9,101,3,6
PO - 4 : Learn approximate reasoning and fuzzy rule based systems.3,4,5,6,7,9,101,3,6
PO - 5 : Get information about Artificial Neural Networks.3,4,5,6,7,9,101,3,6
PO - 6 : Learn Supervised and Unsupervised Learning in Neural Networks.3,4,5,6,7,9,101,3,6
PO - 7 : Learn Neuro-Fuzzy Modeling. Neuro-Fuzzy Control.3,4,5,6,7,9,101,3,6
PO - 8 : Get familiar with the advanced Applications.3,4,5,6,7,9,101,3,6
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

 
Contents of the Course
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
 WeekSubjectRelated Notes / Files
 Week 1A review of fuzzy set theory,
 Week 2fuzzy logic
 Week 3fuzzy decision making
 Week 4approximate reasoning
 Week 5fuzzy relations
 Week 6fuzzy rule based systems.
 Week 7Adaptive Neural Networks.
 Week 8Supervised Learning Neural Networks.Mid-term exam
 Week 9Mid-term exam.
 Week 10Learning from Reinforcement.
 Week 11Unsupervised Learning
 Week 12Other Neural Networks.
 Week 13Neuro-Fuzzy Modeling.
 Week 14Neuro-Fuzzy Control.
 Week 15Neuro-Fuzzy Control
 Week 16End-of-term exam
 
Textbook / Material
1Altaş, İ. H., Lecture Notes, Unpublished.
 
Recommended Reading
1Jang, 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,
2Nauck, D., Klawonn, F., Kruse, R., 1997; Foundations on Neuro-Fuzzy Systems, Wiley, Chichester,
3Klir, G.J. and Folger, T.A., Fuzzy Sets, Uncertainity, and Information, Prentice Hall, Inc.
4Lin, 1996; Neural Fuzzy Systems: A Neuro-Fuzzy Synergism., Prentice Hall.
5Ross, T.J., 1995; Fuzzy Logic with Engineering Applications, McGraw-Hill Book Company, .
 
Method of Assessment
Type of assessmentWeek NoDate

Duration (hours)Weight (%)
Mid-term exam 8 2 30
Project 14 10 20
End-of-term exam 16 2 50
 
Student Work Load and its Distribution
Type of workDuration (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 3 13 39
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 load232