Subjects

Your browser does not support JavaScript, or its support is disabled. Some features may not be available.

Machine Learning in Computer Vision - NPGR035

Title:	Strojové učení v počítačovém vidění
Guaranteed by:	Department of Software and Computer Science Education (32-KSVI)
Faculty:	Faculty of Mathematics and Physics
Actual:	from 2020 to 2022
Semester:	winter
E-Credits:	5
Hours per week, examination:	winter s.:2/2, C+Ex [HT]
Capacity:	unlimited
Min. number of students:	unlimited
Virtual mobility / capacity:	no
State of the course:	taught
Language:	Czech, English
Teaching methods:	full-time
Teaching methods:	full-time

Guarantor:	doc. RNDr. Elena Šikudová, Ph.D.

Opinion survey results Examination dates WS schedule Noticeboard

Annotation -

Last update: RNDr. Tomáš Holan, Ph.D. (08.10.2019)

The course is focused on basic machine learning algorithms used in computer vision tasks. Practical part takes place in a computer lab equipped with Matlab.

Course completion requirements -

Last update: doc. RNDr. Elena Šikudová, Ph.D. (04.06.2018)

http://cgg.mff.cuni.cz/~sikudova/#teaching

Literature -

Last update: T_KSVI (11.05.2017)

Pattern classification / Richard O. Duda, Peter E. Hart, David G. Stork. New York : Wiley Interscience, 2001

Classification pattern recognition and reduction of dimensionality / edited by P. R. Krishnaiah, L. N. Kanal. Amsterdam : North-Holland, 1982

Modern multivariate statistical techniques : Regression, classification, and manifold learning / Alan Julian Izenman. New York : Springer, 2008

Requirements to the exam - Czech

Last update: doc. RNDr. Elena Šikudová, Ph.D. (17.06.2019)

znalost látky probírané na přednáškách

Syllabus -

Last update: doc. RNDr. Elena Šikudová, Ph.D. (28.09.2018)

Classification task, feature- and syntax- based object description.

Feature selection and preprocessing.

Classifiers, basic definitions.

Bayesian decision theory, discriminant functions, separating hypersurfaces, minimum error criterion.

Decision trees.

Discriminant analysis, linear classifier.

Support Vector Machines (SVM).

Neural nets.

Unsupervised learning.

Hidden Markov models.

Classification quality evaluation.

Syntactic pattern recognition, grammatical inference. Special grammar types.