XP33ROD -- Rozpoznávání pro doktorandy (Pattern Recognition)

Introduction, subject goals, eligibility

The subject introduces pattern recognition (called also machine learning).

It is expected that student did not study this subject before, e.g. in the bachelor subject Rozpoznávání a strojové učení, B4M33RPZ, B4M33RPZ lectured by Prof. Jiří Matas. The lecturer will ensure that a similar subject is not taken for the second time to get credits easily.

The subject comprises of lectures and consultations with the lecturer (if the student asks for it).

Expected preliminary knowledge

It is required that the student passed an introductory course of the probability theory and statistics or studied this area individually.


  • 2 x 45 minutes of lecture a week, i.e. 90 minutes in one single lecture.
  • Lectures take place in the room JP:B-633, building B, Praha 6, Jugoslávských partyzánů 1580/3. The lectures are scheduled regularly for Wednesdays from 9:00 to 10:30. However, there irregularites are needed due to the lecturer's business trips. The replacement date will be discussed with the students.
  • If there is one non-Czech speaking student in the audience then the lecture will be given in English. The lecture presentation will be in English typically even if the lecture is given in Czech.
  • Presentations to be given/given at the lecture are available either in English or in Czech or in both languages. The presentation will be typically improved before the lectutre.
Week Date Time Content
0121.02.201809:00 Rehearsal of the basic knowledge from probability theory and statistics. Outline of pattern recognition.
0228.02.201809:00 Bayesian task and its two special cases.
0307.03.201809:00 Non-Bayesian tasks, formulations only. Conditional independence of features. Gaussian models. Feature space straightening.
0407.03.201811:00 Data normalization. Experimental evaluation of classifiers. Receiver operator curve (ROC).
-14.03.2018- No lecture because of V. Hlaváč's busineess trip.
-21.03.2018- No lecture because of V. Hlaváč's busineess trip.
0528.03.201809:00 Estimation of probabilistic models. Parametric methods.
0628.03.201811:00 Estimation of probabilistic models. Nonparametric methods.
0704.04.201809:00 Learning in pattern recognition.
0811.04.201809:00 Linear classifiers. Perceptron. Learning (training) algorithm.
0918.04.201809:00 VC dimension and its use. Support vector machines classifiers (SVM).
1025.04.201809:00 Training algorithms for SVM. Kernel methods.
1102.05.201809:00 Unsupervised learning. Cluster analysis. K-means algorithm.
1209.05.201809:00 Unsupervised learning. EM algorithm.
1309.05.201811:00 Markovian models in pattern recognition.
1416.05.201809:00 Neural networks. Backpropagation. Convolutional networks.

Student's individual work

The student is supposed to develop an own scientifc paper written in English related to the subject domain and (possibly) to her/his own research. The topic is suggested by the student and approved by the teacher. The paper will be in English. The paper draft has to have 8 “Springer proceedings” pages. The paper will be developed in a tool observable/editable by the teacher a.s. Gitlab/LaTeX or Google Docs. The paper draft will be consulted two times with the teacher in the week 6, week 11 at latest. The final version of the paper ha to be delivered in print to the teacher at week 11. The marked version by the teacher on this print will be given back to the student at the week 13.

Examination and its evaluation

  • The exam has two parts, a written test and an oral part. The written test checks the students overview in the subject. In a written part, the student answers typically five questions. The written test counts for 50 points maximally.
  • In the oral part of the exam following the written part, the teacher finds a topic related to students paper (see the individual work above) and related to the subject. The aim of the oral exam is to check if the student knows some part of the subject topic in more detail. The oral part counts for 50 points maximally.
  • The resulting mark follows from the sum of points. The maximal number of points is 100. The evaluation Excellent is for 80 points and more. The evaluation Passed is for 51 points and more. Otherwise the student failed at the exam.


  • 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.
  • Duda R.O., Hart, P.E., Stork, D.G.: Pattern Classification, John Willey and sons, 2nd edition, New York, 2001.
  • Bishop, C.M: Pattern Recognition and Machine Learning, Springer, New York, 2006.

Students of the subject in the summer semester 2017/2018

Registered students:

Zagroz Abdulkhaliq Aziz (azizzagr@fel.cvut.cz), Maria Rigaki (maria.rigaki@fel.cvut.cz), Kiriaki-Maria Saiti (krks1988@gmail.com), Gabriela Šejnová (sejnogab@fel.cvut.cz), Petr Švarný (svarnpet@fel.cvut.cz), Michael Tesař (tesarm11@fel.cvut.cz)

Students which have to register:

Jan Hauser (hauser.jan@fel.cvut.cz), Václav Mácha (machava2@fjfi.cvut.cz),

Extraordinary students (visiting students working for 4 months with V. Hlaváč) Richard Lengyel (Hungary), Matthias De Ryck (Belgium)

courses/xp33rod/start.txt · Last modified: 2018/03/08 11:30 by hlavac