1. Homepage
  2. Master of Science in Materials Science and Nanotechnology (Interdisciplinary) (Thesis)
  3. Course Plans
  4. Sinir Ağları ve Bulanık Sistemler

PDF

COURSE DESCRIPTION AND APPLICATION INFORMATION

Course Name Code Semester T+A+L (hour/week) Type (C / O) Local Credit ECTS
Neural Networks and Fuzzy Systems CE 511 Fall 03+00+00 Elective 3 7.5
Academic Unit:
Mode of Delivery: Face to face
Prerequisites: None
Language of Instruction: English
Level of Course Unit: Graduate
Course Coordinator: Habib ŞENOL
Course Objectives: To provide information on the classification of artificial neural networks (ANN), to provide information on the classification of fuzzy systems, to provide information on the classification of neural-network-based fuzzy systems.
Course Contents: Artificial neural networks: radial-basis function networks structure adaptive neural networks applications of neural networks. Fuzzy-neural integrated systems: integrating fuzzy systems and neural networks neural-network-based fuzzy systems fuzzy-logic-based neural models applications. Fuzzy Systems: basics of fuzzy systems fuzzy measures fuzzy logic and approximate Reasoning applications of fuzzy theory.
Learning Outcomes of the Course Unit (LO):
    Planned Learning Activities and Teaching Methods: Lecture


    WEEKLY SUBJECTS AND RELATED PREPARATIONS

    WeekSubjectsRelated Preperation


    REQUIRED AND RECOMMENDED READING

    Lin, C. T., Lee, C. S. G., 1995. "Neural Fuzzy Systems", Prentice Hall.


    OTHER COURSE RESOURCES

    Haykin, S., 1999. "Neural Networks - A Comprehensive Foundation", Second
    Edition, Prentice Hall,

    Yen, J., 1999. "Fuzzy Logic", Prentice Hall.


    ASSESSMENT METHODS AND CRITERIA

    Semester RequirementsNumberPercentage of Grade (%)
    Total: 0 0


    WORKLOAD

    EventsCountDuration (Hours)Total Workload (hour)
    Total Workload (hour):0


    THE RELATIONSHIP BETWEEN COURSE LEARNING OUTCOMES (LO) AND PROGRAM QUALIFICATIONS (PQ)

    # PQ1 PQ2 PQ3 PQ4 PQ5 PQ6 PQ7 PQ8