Description:

Collection of recognition and classification methods with accent to mathematical and statistical principles of their design
and functionality.

Contents:

1.Introduction - what is pattern recognition and decision making
2.Statistical (feature-based) and structural (syntactic) pattern recognition
3.Introduction to statistical pattern recognition - supervised and non-supervised classifiers
4.Simple metric classifiers - NN classifier, k-NN classifier, linear classifier
5.Bayesian classifier - the basic principle, parametric and non-parametric B.c., B.c. for normally distributed classes, parameter estimation, necessary conditions of linearity, special cases in two dimensions
6.Non-metric classifiers, decision trees
7.Non-supervised classifiers - cluster analysis in the feature space, iterative and hierarchical methods, criteria of cluster separability
8.k-means iterative algorithm and its modifications
9.Agglomerative hierarchical clustering, inter-cluster metrics, stop conditions, estimating the number of clusters
10.Dimensionality reduction of the feature space, feature extraction and selection, class separability criteria, Mahalanobis distance
11.Principal component transform
12.Optimal and sub-optimal feature selection methods, sequential and floating search
13.Decision making as a discrete optimization problem
14.Basic methods for unconstrained and constrained discrete optimization

Recommended literature:

Key references:
[1] Urbanowicz, R. J. J., Browne, W. N. Introduction to Learning Classifier Systems. Berlin: Springer, 2017.
[2] Matloff, N. Statistical Regression and Classification: From Linear Models to Machine Learning. Boca Raton: CRC
press, 2017.
Recommended references:
[3] Duda, R. O., Hart, P. E., Stork, D. G. Pattern Classification. 2nd edition. New York: Willey, 2007.
[4] Scholkopf, B., Smola, A. J. Learning with Kernels. Cambridge: MIT Press, 2001.
[5] Aggarwal, Ch. C. Data Mining: The Textbook. Cham (Switzerland): Springer, 2015.
[6] Izenman, A. J. Modern Multivariate Statistical Techniques: Regression, Classification, and Manifold Learning.
Corr. 2nd printing 2013 edition. New York: Springer, 2013.
[7] Proceedings of the International Workshop on Multiple Classifier Systems (MCS).

Keywords:

pattern set, classification, classifier, metric space, vector space, statistical methods, kernel methods, cross-validation

Abbreviations used:

Semester:

• W ... winter semester (usually October - February)
• S ... spring semester (usually March - June)
• W,S ... both semesters

Mode of completion of the course:

• A ... Assessment (no grade is given to this course but credits are awarded. You will receive only P (Passed) of F (Failed) and number of credits)
• GA ... Graded Assessment (a grade is awarded for this course)
• EX ... Examination (a grade is awarded for this course)
• A, EX ... Examination (the award of Assessment is a precondition for taking the Examination in the given subject, a grade is awarded for this course)

Weekly load (hours per week):

• P ... lecture
• C ... seminar
• L ... laboratory
• R ... proseminar
• S ... seminar