Graduate Study - Faculty of Engineering and Natural Sciences
PhD Information Technology

Code Name Level Year Semester
CEN 671 Special Topics in Pattern Recognition Graduate 1 Spring
Status Number of ECTS Credits Class Hours Per Week Total Hours Per Semester Language
6 160

Instructor Assistant Coordinator
Abdülhamit Subaşı, Prof. Dr. Abdülhamit Subaşı, Prof. Dr.
[email protected] no email

This course deals with the fundamentals of characterizing and recognizing patterns and features of interest in numerical data. We discuss the basic tools and theory for signal understanding problems with applications to user modelling, affect recognition, speech recognition and understanding, computer vision, physiological analysis, and more. We also cover decision theory, statistical classification, maximum likelihood and Bayesian estimation, nonparametric methods, unsupervised learning and clustering. Additional topics on machine and human learning from active research are also talked about in the class.

  1. Introduction to statistical pattern recognition
  2. Maximum likelihood and Bayesian parameter estimation
  3. Classifiers Based on Bayes Decision Theory
  4. Linear regression
  5. Linear Classifiers
  6. Nonlinear Classifiers
  7. Multilayer Neural Networks
  8. Nonparametric techniques (k-NN)
  9. Decision Tree Based Methods
  10. Feature Extraction and Selection
  11. Data Transformation and Dimensionality Reduction
  12. Template Matching
  13. Context Dependent Classification (HMM)
  14. System Performance Evaluation
  15. Unsupervised Learning and Clustering


    • Lectures
    • Presentation
    • Project
    • Assignments
    Description (%)
    Method Quantity Percentage (%)
    Final Exam135
    Total: 100
    Learning outcomes
    • Demonstrate a systematic and critical understanding of the theories, principles and practices of pattern recognition;
    • Creatively apply contemporary theories, processes and tools in the development and evaluation of solutions to problems in pattern recognition;
    • Actively participate in, reflect upon, and take responsibility for, personal learning and development, within a framework of lifelong learning and continued professional development;
    • Present issues and solutions in appropriate form to communicate effectively with peers and clients from specialist and non-specialist backgrounds;
    • Work with minimum supervision, both individually and as a part of a team, demonstrating the interpersonal, organisation and problem-solving skills supported by related attitudes necessary to undertake employment.
    • 1. S. Theodoridis, A. Pikrakis, K. Koutroumbas, D. Cavouras, Introduction to Pattern Recognition A MATLAB® Approach, Academic Press, Elsevier Inc. 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) 0
    Final Examination(1 week)133
    Preparation for Midterm Examination 0
    Preparation for Final Examination11515
    Assignment / Homework/ Project24080
    Seminar / Presentation21020
    Total Workload: 160
    ECTS Credit (Total workload/25): 6