Welcome, Guest . Login . Türkçe
Where Am I: Ninova / Courses / Institute of Science and Technology / TEL 531E - İstatistiksel Örüntü ASnalizi ve Sınıflandırma

TEL 531E - Statistical Pattern Analysis and Classification

Course Objectives

To provide information about the fundamentals of statistical pattern analysis and classification with examples from several application areas.
To cover techniques for handling multidimensional data of various types and scales along with algorithms for clustering and classification.

Course Description

Basic concepts : feature vectors, covariance matrix, expected value, variance, mean. Multidimensional probability distributions. Error probability and ROC. Decision surfaces and discriminant functions. Parametric pattern classification techniques: Bayes decision theory. Parameter estimation by maximum likelihood and maximum a posterior density. Support vector machines. Nonparametric pattern classifiers. Mixture models. Clustering. Feature dimension reduction by eigenvalue decomposition. Feature subset selection.

Course Coordinator
Bilge Günsel Kalyoncu
Course Language
Courses . Help . About
Ninova is an ITU Office of Information Technologies Product. © 2021