|
| |
|
| |
|
|
Vyhodnocení stability jednotlivých metod i skupin metod výběru příznaků, který optimalizují kardinalitu podmnožiny příznaků
Somol, Petr ; Novovičová, Jana
Stability (robustness) of feature selection methods is a topic of recent interest yet often neglected importance with direct impact on the reliability of machine learning systems. We investigate the problem of evaluating the stability of feature selection processes yielding subsets of varying size. We introduce several novel feature selection stability measures and adjust some existing measures in a unifying framework that offers broad insight into the stability problem. We study in detail the properties of considered measures and demonstrate on various examples what information about the feature selection process can be gained. We also introduce an alternative approach to feature selection evaluation in form of measures that enable comparing the similarity of two feature selection processes. These measures enable comparing, e.g., the output of two feature selection methods or two runs of one method with different parameters. The information obtained using the considered stability and similarity measures is shown usable for assessing feature selection methods (or criteria) as such
|
|
|
Zobecněný váleček
Haindl, Michal ; Hatka, Martin
This paper describes a generalization of our previously published simple roller method for seamless enlargement of colour textures such as natural bidirectional texture functions (BTF) that realistically represent appearance of given material surfaces. The generalized roller allows automatic detection of major texture periodicity directions which do not need to be aligned with coordinate axes. The roller texture synthesis method is based on the overlapping tiling and subsequent minimum error boundary cut. One or several optimal double toroidal BTF patches are seamlessly repeated during the synthesis step. While the method allows only moderate texture compression it is extremely fast due to complete separation of the analytical step of the algorithm from the texture synthesis part. The method is universal and easily implementable in a graphical hardware for purpose of real-time rendering of any type of static or dynamic textures.
|
|
|
Diagnostické vyhodnocování screeningových mamogramů pomocí lokálních texturních modelů
Grim, Jiří ; Somol, Petr
We propose statistically based preprocessing of screening mammograms with the aim to emphasize suspicious areas. We estimate the local statistical texture model of a single mammogram in the form of multivariate Gaussian mixture. The probability density is estimated from the data obtained by pixelwise scanning of the mammogram with the search window. In the second phase, we evaluate the estimated density at each position of the window and display the corresponding log-likelihood value as a gray level at the window center. Light gray levels correspond to the typical parts of the image and the dark values reflect unusual places. The resulting log-likelihood image exactly correlates with the structural details of the original mammogram, emphasizes locations of similar properties by contour lines and may provide additional information to facilitate diagnostic interpretation.
|
|
|
Informační shlukování kategoriálních dat
Hora, Jan
The EM algorithm has been used repeatedly to identify latent classes in categorical data by estimating finite distribution mixtures of product components. Unfortunately, the underlying mixtures are not uniquely identifiable and, moreover, the estimated mixture parameters are starting-point dependent. For this reason we use the latent class model only to define a set of ``elementary'' classes by estimating a mixture of a large number components. As such a mixture we use also an optimally smoothed kernel estimate. We propose a hierarchical ``bottom up'' cluster analysis based on unifying the elementary latent classes sequentially. The clustering procedure is controlled by minimum information loss criterion.
|
|
|
Kompozicionální modely domněnkvých funkcí
Jiroušek, Radim ; Vejnarová, Jiřina ; Daniel, Milan
After it has been successfully done in probability and possibility theories, the paper is the first attempt to introduce the operator of composition also for belief functions. We prove that the proposed definition preserves all the necessary properties of the operator enabling us to define compositional models as an efficient tool for multidimensional models representation.
|
|
|
Podmíněná nezávislost ve věrohodnostních funkcích: Příklady
Jiroušek, Radim
The paper presents an additional possibility how to define conditional independence relation for belief functions. The approach is based on the operator of composition originally designed for multidimensional model processing. Not to make confusion with the preceding definitions we call this relation conditional irrelevance. In the paper examples illustrating properties of this relation are presented.
|
|
|
Efektivní algoritmus na hledání redukcí v kompozicionálních modelech
Kratochvíl, Václav
This paper deals with the problem of marginalization of multidimensional probability distributions represented by a compositional model. By the perfect one in this case. From the computational point of view this solution is more efficient than any known marginalization process for Bayesian models. This is because the process mentioned in the paper in a form of an algorithm and takes an advantage of the fact that the perfect sequence models have some information encoded; if can be obtained from the Bayesian networks by an application of rather computationally expensive procedures. One part of that algorithm is marginalization by means of reduction. This paper describe a new faster algorithm to find a reduction in a compositional model.
|
|
|
Využití imsetů při učení bayesovských sítí
Vomlel, Jiří ; Studený, Milan
This paper describes a modification of the greedy equivalence search (GES) algorithm. The presented modification is based on the algebraic approach to learning. The states of the search space are standard imsets. Each standard imset represents an equivalence class of Bayesian networks. For a given quality criterion the database is represented by the respective data imset. This allows a very simple update of a given quality criterion since the moves between states are represented by differential imsets. We exploit a direct characterization of lower and upper inclusion neighborhood, which allows an efficient search for the best structure in the inclusion neighborhood. The algorithm was implemented in R and is freely available.
|
guest ::
