Search

Your search keyword '"Janáček, Patrik"' showing total 6 results
Start Over Author "Janáček, Patrik"
6 results on '"Janáček, Patrik"'

1. Robustness Aspects of Optimized Centroids

Author

Kalina, Jan, Janáček, Patrik, Gaul, Wolfgang, Managing Editor, Vichi, Maurizio, Managing Editor, Weihs, Claus, Managing Editor, Baier, Daniel, Editorial Board Member, Critchley, Frank, Editorial Board Member, Decker, Reinhold, Editorial Board Member, Diday, Edwin, Editorial Board Member, Greenacre, Michael, Editorial Board Member, Lauro, Carlo Natale, Editorial Board Member, Meulman, Jacqueline, Editorial Board Member, Monari, Paola, Editorial Board Member, Nishisato, Shizuhiko, Editorial Board Member, Ohsumi, Noboru, Editorial Board Member, Opitz, Otto, Editorial Board Member, Ritter, Gunter, Editorial Board Member, Schader, Martin, Editorial Board Member, Brito, Paula, editor, Dias, José G., editor, Lausen, Berthold, editor, Montanari, Angela, editor, and Nugent, Rebecca, editor

Published
2023
Full Text
View/download PDF

3. Testing exchangeability of multivariate distributions.

Author

Kalina, Jan and Janáček, Patrik

Subjects
*DISTRIBUTION (Probability theory), *BIVARIATE analysis, *MULTIPLE comparisons (Statistics)
Abstract

Although there have been a number of available tests of bivariate exchangeability, i.e. bivariate symmetry for bivariate distributions, the literature is void of tests whether a multivariate distribution with more than two dimensions is exchangeable or not. In this paper, multivariate permutation tests of exchangeability of multivariate distributions are proposed, which are based on the non-parametric combination methodology, i.e. on combining non-parametric bivariate exchangeability tests. Numerical experiments on real as well as simulated multivariate data with more than two dimensions are presented here. The multivariate permutation test turns out to be typically more powerful than a bivariate exchangeability test performed only over a single pair of variables, and also more suitable compared to tests exploiting the approaches of Benjamini–Yekutieli or Bonferroni. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

4. Robust regression and robust neural networks

Author

Janáček, Patrik, Kalina, Jan, and Maciak, Matúš

Subjects
robustnost|strojové učení|regrese, robustness|machine learning|regression
Abstract

The classical least squares approach in linear regression is prone to the presence of outliers in the data. The aim of this thesis is to present several robust alternatives to the least squares method in the linear regression framework and discuss their properties. Then robust neural networks based on these estimators are introduced and compared in a simulation study. In particular, the least weighted squares method with adaptive weights seems promising, as it is able to combine high robustness with efficiency in the absence of contamination in the data. 1

Published
2023

6. Optimalizační metody prvního řádu v úlohách strojového učení

Author

Janáček, Patrik, Branda, Martin, and Kozmík, Karel

Subjects
Computer Science::Machine Learning, MathematicsofComputing_NUMERICALANALYSIS, Stochastický gradient, strojové učení, Stochastic gradient, machine learning, optimization, optimalizace
Abstract

The goal of the thesis is to introduce the stochastic gradient method for optimizing differentiable objective function and discuss its convergence. First, supervised learning and empirical risk minimization (ERM) are explained. Then stochastic gradient descent (SG) is itroduced and analysed, first in the context of strictly convex objective function and then for the general non-convex function. In the last part, the classification of email spam is practically solved. 1

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results