Türkçe | English
GRADUATE INSTITUTE of NATURAL and APPLIED SCIENCES / DEPARTMENT of STATISTICS and COMPUTER SCIENCES
Statistics-Joint Doctorate
Course Catalog
https://www.ktu.edu.tr/fbeistatistik
Phone: +90 0462 +90 (462) 377 3112
FBE
GRADUATE INSTITUTE of NATURAL and APPLIED SCIENCES / DEPARTMENT of STATISTICS and COMPUTER SCIENCES / Statistics-Joint Doctorate
Katalog Ana Sayfa
  Katalog Ana Sayfa  KTÜ Ana Sayfa   Katalog Ana Sayfa
 
 

ISTL7063Statistical Pattern Recognition3+0+0ECTS:7.5
Year / SemesterFall Semester
Level of CourseThird Cycle
Status Elective
DepartmentDEPARTMENT of STATISTICS and COMPUTER SCIENCES
Prerequisites and co-requisitesNone
Mode of Delivery
Contact Hours14 weeks - 3 hours of lectures per week
LecturerDr. Öğr. Üyesi Uğur ŞEVİK
Co-LecturerAsst. Prof. Uğur ŞEVİK
Language of instructionTurkish
Professional practise ( internship ) None
 
The aim of the course:
This course will examine various statistical models and popular pattern recognition algorithms. Two complementary approaches will be used for discrimination of data. Calculating the probability density function, Bayes theorem approach and discriminant function approach will be presented.
 
Programme OutcomesCTPOTOA
Upon successful completion of the course, the students will be able to :
PO - 1 : Be able to comprehend the fundamental principles and notions of statistical pattern recognition systems. 1 - 21,3,5,
PO - 2 : Be able to decide the most suitable classifier for a given classification problem 1 - 21,3,5,
PO - 3 : Be able to extract discriminatory features from datasets 1 - 21,3,5,
PO - 4 : Be able to understand the principles of supervised and unsupervised learning, and generalization ability. 1 - 21,3,5,
PO - 5 : Be able to design and evaluate the performance of statistical pattern recognition system for a given task. 1 - 21,3,5,
PO - 6 : Be able to code the algorithms on a computer. 1 - 21,3,5,
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
The topics of this course are Bayesian Classifiers, Maximum Likelihood Estimation, Hidden Markov Models, Bayesian Parameter Estimation, K-Nearest Neighbor Classifier, Linear Separators, Multilayer Neural Networks, Support Vector Machines, K-Means Clustering and Feature Selection.
 
Course Syllabus
 WeekSubjectRelated Notes / Files
 Week 1Introduction to Statistical Pattern Recognition
 Week 2Density Estimation - Parametric
 Week 3Density Estimation - Bayesian
 Week 4Density Estimation ? Non-Parametric (k-NN, Histogram Based Approaches)
 Week 5Density Estimation ? Non-Parametric (Kernel Methods )
 Week 6Linear Discriminant Analysis
 Week 7Non-Linear Discriminant Analysis ( Radial Basis Functions)
 Week 8Non-Linear Discriminant Analysis ( Non-Linear SVM)
 Week 9MIDTERM
 Week 10Rule and Decision Tree Induction
 Week 11Classifier Combination Methods
 Week 12Performance Assessment
 Week 13Feature Extraction
 Week 14Feature Selection
 Week 15Clustering
 Week 16FINAL EXAM
 
Textbook / Material
1Statistical Pattern Recognition, A. Webb, 3rd. Edition, Wiley, 2011.
2Pattern Classification: R.O. Duda, P.E. Hart, D.G. Stork 2. Baskı, Wiley, 2000.
 
Recommended Reading
1Introduction to Statistical Pattern Recognition, K. Fukunaga, Academic Press, 1990.
2Pattern Recognition, S. Theodoridis, K. Koutroumbas, 3rd edition, Academic Press, 2006.
3Introduction to Machine Learning: E. Alpaydın, MIT Press, 2004.
 
Method of Assessment
Type of assessmentWeek NoDate

Duration (hours)Weight (%)
Mid-term exam 8 18/11/2025 2 30
Quiz 12 09/12/2025 2 20
End-of-term exam 16 06/01/2026 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 8 14 112
Arasınav için hazırlık 6 1 6
Arasınav 2 1 2
Dönem sonu sınavı için hazırlık 10 1 10
Dönem sonu sınavı 2 1 2
Total work load174