INTERNATIONAL BURCH UNIVERSITY
Graduate Study - Faculty of Engineering and Natural Sciences
3+2 Electrical and Electronic Engineering
2015-2016

SYLLABUS
Code Name Level Year Semester
EEE 544 Computational Intelligence Graduate 1 Spring
Status Number of ECTS Credits Class Hours Per Week Total Hours Per Semester Language
Area Elective 6 3 150 English

Instructor Assistant Coordinator
Jasna Hivziefendi─ç, Assist. Prof. Dr. Jasmin Kevric Jasna Hivziefendi─ç, Assist. Prof. Dr.
[email protected] [email protected] no email

This course begins with an introductions to soft computing, from fuzzy logic to genetic algorithms. After a thorough study of fuzzy logic systems, concept of machine learning in general is introduced. Major classes of machine learning are covered and implemented in various scenarios.

COURSE OBJECTIVE
This course should provide the student ability to observe data mining and machine learning methods in terms of embedded systems framework and to implement machine learning algorithms in various platforms.

COURSE CONTENT
Week
Topic
  1. Introduction to computational intelligence
  2. Fuzzy Logic Systems
  3. Artificial Neural Networks
  4. Evolutionary computation: Genetic Algorithms
  5. Particle Swarm Optimization
  6. Feature Reduction: PCA, ICA
  7. Midterm Review
  8. MIDTERM EXAM
  9. Post-midterm Review
  10. Nearest Neighbor Algorithm
  11. Support Vector Machines
  12. Unsupervised learning: Clustering
  13. Microsoft Azure
  14. Deep Learning: Google TensorFlow
  15. Final Exam Review

LABORATORY/PRACTICE PLAN
Week
Topic

    TEACHING/ASSESSMENT
    Description
    • Interactive Lectures
    • Excersises
    • Discussions and group work
    Description (%)
    Method Quantity Percentage (%)
    Midterm Exam(s)120
    Lab/Practical Exam(s)130
    Attendance110
    Final Exam140
    Total: 100
    Learning outcomes
    • Gain a working knowledge of knowledge-based systems, neural networks, fuzzy
    • Apply intelligent systems technologies in a variety of engineering applications
    • Implement typical computational intelligence algorithms in MATLAB, WEKA, TensorlFlow, or Azure
    • Present ideas and findings effectively
    • Think critically and learn independently
    TEXTBOOK(S)
    • S. Theodoridis, K. Koutroumbas, An Introduction to Pattern Recognition: A MATLAB Approach, 2010.

    ECTS (Allocated based on student) WORKLOAD
    Activities Quantity Duration (Hour) Total Work Load
    Lecture (14 weeks x Lecture hours per week)14342
    Laboratory / Practice (14 weeks x Laboratory/Practice hours per week) 0
    Midterm Examination (1 week)122
    Final Examination(1 week)122
    Preparation for Midterm Examination13535
    Preparation for Final Examination13535
    Assignment / Homework/ Project11717
    Seminar / Presentation11717
    Total Workload: 150
    ECTS Credit (Total workload/25): 6