XP33ROD - Pattern Recognition for doctoral students

Summer semestr 2008/2009, 2 hours lectures, personal assignment equivalent to 2 hours exercises per week.

The lecture is given on Mondays from 14:30 to 16:00 in the seminar room G205, building G of the Faculty of Electrical Engineering at the Czech Technical University Campus at Karlovo náměstí. If there is one student enrolled who does not understand Czech then the lectures will be given in English, otherwise in Czech. Most of the presentations are in English too.

The subject XP33ROD je intended as an introductory one for doctoral students who did not pass the subject 33RPZ Pattern Recognition which is taught by Doc. Ing. Jiří Matas, PhD. in the MSc study program or those who like to see the topic through eyes of another teacher. For others,  a more advanced subject  XP33ROZ is available. Interested students have to contact Jiří Matas.

Lecturers:  

prof. Ing. Václav Hlaváč, CSc.,  prof. Ing. Vladimír Mařík, DrSc.
Katedra kybernetiky, Fakulta elektrotechnická ČVUT
hlavac@cmp.felk.cvut.cz, marik@fel.cvut.cz 


 Exercises instructor:  prof. Ing. Václav Hlaváč, CSc.

Students have two options how to pass exercises. One of the two options or both can be selected.

  1. Participate in the exercises taught for master students in the subject 33RPZ. Make your arrangements with the instructors of the subject and inform me (V. Hlaváč) about it before you start attending the exercises. The content of exercises can be modified according to previous experience of the student and according to student's research interest.
  2. Solve an individual assignment which is related to the subject. This option has to be negotiated in advanced with V. Hlaváč.

Praha, February 16, 2009

 

Plan of the lectures

Week of a semester

Lecturer

Date

Topic of the lecture
1 V. Hlaváč 2.03.2009 Introduction. Basic concepts. Formulation of the basic tasks solved in pattern recognition. Rehearsal of basic knowledge from probability theory and statistics.
2 V. Hlaváč 9.03.2009 Bayesian task.Non-Bayesian tasks.
3 V. Hlaváč 16.03.2009 Two special useful statistical models. Conditional independence of features. Gaussian models. Strightening of the feature space.
4 V. Hlaváč 23.03.2009 Experimental evaluation of classifiers. Receiver operator curve (ROC).
5 V. Franc 30.03.2009 Estimation of probabilistic models. Parametric and nonparametric methods.
6 V. Hlaváč 6.04.2009 Learning in pattern recognition. VC dimension. Estimate of the needed length of the training sequence.
7 No one 13.04.2009 Holiday. Easter Monday.
8 V. Hlaváč 20.04.2009 Linear classifiers and their learning. Support vector machines classifiers (SVM).
9 V. Hlaváč 27.04.2009 Kernel methods.
10 V. Hlaváč 4.05.2009  Unsupervised learning. Cluster analysis. EM (Expectation Maximization) algorithm.
11 V. Hlaváč 11.05.2009  Intro to structural methods embedded into the statistical framework. Recognition of Markovian sequences.
12  V. Hlaváč  18.05.2009  Recognition of Markovian sequences (continuation). 2D grammars for images.
13 V. Mařík

25.05.2009

Structural pattern recognition, a classical approach.
14 V. Mařík 1.06.2009 Experiences learned from practial implementations of pattern recognition methods.

Recommended literature:

  1. Schlesinger M.I., Hlaváč V.: Ten lectures on statistical and structural pattern recognition, Kluwer Academic Publishers, Dordrecht, The Netherlands, 2002. Edition in Czech Vydavatelství ČVUT Praha, 1999.
  2. Duda R.O., Hart, P.E.,Stork, D.G.: Pattern Classification, John Willey and sons, 2nd edition, New York, 2001.
  3. Bishop, C.M: Pattern Recognition and Machine Learning, Springer, New York, 2006.

Presentations (It is likely that presentation will be updated before the lecture): Follow the www pages with presentations V. Hlavac maintains: in English, in Czech. Presentation of V. Franc about probability distributions estimation, click here.

Poslední změna 02.04. 2009 V. Hlaváč, hlavac@fel.cvut.cz