Robust Metalearning: Comparing Robust Regression Using A Robust Prediction Error
Peštová, Barbora; Kalina, Jan
2018 - English The aim of this paper is to construct a classification rule for predicting the best regression estimator for a new data set based on a database of 20 training data sets. Various estimators considered here include some popular methods of robust statistics. The methodology used for constructing the classification rule can be described as metalearning. Nevertheless, standard approaches of metalearning should be robustified if working with data sets contaminated by outlying measurements (outliers). Therefore, our contribution can be also described as robustification of the metalearning process by using a robust prediction error. In addition to performing the metalearning study by means of both standard and robust approaches, we search for a detailed interpretation in two particular situations. The results of detailed investigation show that the knowledge obtained by a metalearning approach standing on standard principles is prone to great variability and instability, which makes it hard to believe that the results are not just a consequence of a mere chance. Such aspect of metalearning seems not to have been previously analyzed in literature. Keywords: metalearning; robust regression; outliers; robust prediction error Fulltext is available at external website. Robust Metalearning: Comparing Robust Regression Using A Robust Prediction Error

The aim of this paper is to construct a classification rule for predicting the best regression estimator for a new data set based on a database of 20 training data sets. Various estimators considered ...

Peštová, Barbora; Kalina, Jan
Ústav informatiky, 2018

Popis TDD modelu verze 3.9
Novák, Jakub; Jiřina, M.; Benešová, Michaela
2018 - Czech Zpráva je závěrečnou roční zprávou pro rok 2018 v rámci Projektu TDD-ČR. Cílem je předat metodiky pro užití modelu jak provozovatelem distribuční soustavy, tak operátorem trhu a dále informovat o aktuálním stavu modelu. Jsou popsány předávané soubory včetně vzorového výpočtu na reálných datech a jejich obsah. Keywords: typový diagram dodávky; typový diagram dodávky; spotřeba plynu; TDD; popis modelu Available at various institutes of the ASCR Popis TDD modelu verze 3.9

Zpráva je závěrečnou roční zprávou pro rok 2018 v rámci Projektu TDD-ČR. Cílem je předat metodiky pro užití modelu jak provozovatelem distribuční soustavy, tak operátorem trhu a dále informovat o ...

Novák, Jakub; Jiřina, M.; Benešová, Michaela
Ústav informatiky, 2018

A limited-memory optimization method using the infinitely many times repeated BNS update and conjugate directions
Vlček, Jan; Lukšan, Ladislav
2018 - English Keywords: Unconstrained minimization; variable metric methods; limited-memory methods; the repeated BFGS update; global convergence; numerical results Available in digital repository of the ASCR A limited-memory optimization method using the infinitely many times repeated BNS update and conjugate directions

Vlček, Jan; Lukšan, Ladislav
Ústav informatiky, 2018

Numerical solution of generalized minimax problems
Lukšan, Ladislav; Matonoha, Ctirad; Vlček, Jan
2018 - English Keywords: Numerical optimization; nonlinear approximation; nonsmooth optimization; generalized minimax problems; recursive quadratic programming methods; interior point methods; smoothing methods; algorithms; numerical experiments Available in digital repository of the ASCR Numerical solution of generalized minimax problems

Lukšan, Ladislav; Matonoha, Ctirad; Vlček, Jan
Ústav informatiky, 2018

Soupis publikovaých prací pana prof. Ing. Mirko Nováka, DrSc. zpracovaný ke dni 13. dubna 2018 knihovnou Ústavu informatiky AV ČR, v. v. i. s ohledem na dostupnost uvedených prací
Nývltová, Ludmila; Ramešová, Nina; Šírová, Tereza
2018 - Czech Keywords: bibliografie Available in digital repository of the ASCR Soupis publikovaých prací pana prof. Ing. Mirko Nováka, DrSc. zpracovaný ke dni 13. dubna 2018 knihovnou Ústavu informatiky AV ČR, v. v. i. s ohledem na dostupnost uvedených prací

Nývltová, Ludmila; Ramešová, Nina; Šírová, Tereza
Ústav informatiky, 2018

Návrh integrovaného emisního procesoru nové generace
Resler, Jaroslav; Juruš, Pavel; Benešová, N.; Vlček, O.; Belda, M.; Huszár, P.; Krč, Pavel; Eben, Kryštof
2017 - Czech V podstatě jediným rozšířeným a veřejně dostupným nástrojem pro modelování emisí pro potřeby CTM je procesor SMOKE (Coats & Carlie, 1996). Problém modelu SMOKE ovšem je v jeho silné vazbě na podmínky USA. V minulosti došlo k několika pokusům uzpůsobit model SMOKE jiným podmínkám - viz např. práce reportované v Bieser et al., 2011 nebo Borge et al., 2008, úsilí ovšem vždy naráželo na limity designu tohoto emisního procesoru. Naším cílem je vyvinout emisní procesor založený na otevřených technologiích, který bude komfortní pro typické využití v CTM v našich podmínkách a který bude dostatečně flexibilní, aby byl snadno konfigurovatelný a nastavitelný i pro ostatní uživatele ve světě a jejich specifické potřeby. The only publicly available and widely used tool for emission modelling for CTM is the processor SMOKE (Coats & Carlie, 1996), but its usage is limited by its strong dependence on conditions of USA. A few attempts to adjust SMOKE to other conditions were made in the past - see e.g. works reported in Bieser et al., 2011 or Borge et al., 2008, but the efforts hit the limits of its design. Our goal is to develop an emission processor based on open technologies which will be easy to use for typical usage with CTM in our conditions and which will be flexible and configurable enough to serve specific needs of users in other countries over the world. Keywords: emission model; CTM; postgresql; postgis; inventory Available at various institutes of the ASCR Návrh integrovaného emisního procesoru nové generace

V podstatě jediným rozšířeným a veřejně dostupným nástrojem pro modelování emisí pro potřeby CTM je procesor SMOKE (Coats & Carlie, 1996). Problém modelu SMOKE ovšem je v jeho silné vazbě na podmínky ...

Resler, Jaroslav; Juruš, Pavel; Benešová, N.; Vlček, O.; Belda, M.; Huszár, P.; Krč, Pavel; Eben, Kryštof
Ústav informatiky, 2017

The Computational Power of Neural Networks and Representations of Numbers in Non-Integer Bases.
Šíma, Jiří
2017 - English We briefly survey the basic concepts and results concerning the computational power of neural networks which basically depends on the information content of weight parameters. In particular, recurrent neural networks with integer, rational, and arbitrary real weights are classified within the Chomsky and finer complexity hierarchies. Then we refine the analysis between integer and rational weights by investigating an intermediate model of integer-weight neural networks with an extra analog rational-weight neuron (1ANN). We show a representation theorem which characterizes the classification problems solvable by 1ANNs, by using so-called cut languages. Our analysis reveals an interesting link to an active research field on non-standard positional numeral systems with non-integer bases. Within this framework, we introduce a new concept of quasi-periodic numbers which is used to classify the computational power of 1ANNs within the Chomsky hierarchy. Keywords: neural network; Chomsky hierarchy; beta-expansion; cut language Available at various institutes of the ASCR The Computational Power of Neural Networks and Representations of Numbers in Non-Integer Bases.

We briefly survey the basic concepts and results concerning the computational power of neural networks which basically depends on the information content of weight parameters. In particular, recurrent ...

Šíma, Jiří
Ústav informatiky, 2017

Semigroup Structure of Sets of Solutions to Equation X^s = X^m
Porubský, Štefan
2017 - English Using an idempotent semigroup approach we describe the semigroup and group structure of the set of solutions to equation X^m = X^s in successive steps over a periodic commutative semigroup, over multiplicative semigroups of factor rings of residually finite commutative rings and finally over multiplicative semigroups of factor rings of residually finite commutative principal ideal domains. The analysis is done through the use of the maximal subsemigroups and groups corresponding to an idempotent of the corresponding semigroup and in the case of residually finite PID’s employing the available analysis of the Euler-Fermat Theorem as given in [11]. In particular the case when this set of solutions is a union of groups is handled. As a simple application we show a not yet noticed group structure of the set of solutions to x^n = x connected with the message space of RSA cryptosystems and Fermat pseudoprimes. Keywords: set of solutions; idempotent; maximal semigroup corresponding to an idempotent; maximal group corresponding to an idempotent; equation X^s = X^m; finite commutative ring with identity element; residually finite commutative principal ideal domains Available on request at various institutes of the ASCR Semigroup Structure of Sets of Solutions to Equation X^s = X^m

Using an idempotent semigroup approach we describe the semigroup and group structure of the set of solutions to equation X^m = X^s in successive steps over a periodic commutative semigroup, over ...

Porubský, Štefan
Ústav informatiky, 2017

An adaptive recursive multilevel approximate inverse preconditioning: Computation of the Schur complement
Kopal, Jiří; Rozložník, Miroslav; Tůma, Miroslav
2017 - English Available in digital repository of the ASCR An adaptive recursive multilevel approximate inverse preconditioning: Computation of the Schur complement

Kopal, Jiří; Rozložník, Miroslav; Tůma, Miroslav
Ústav informatiky, 2017

Stav předaných dat a úprava rozdělení vybraných měření 2017
Novák, Jakub; Jiřina jr., M.; Benešová, Michaela
2017 - Czech Keywords: typový diagram dodávky; TDD; spotřeba plynu; měřící místa; kritéria; filtrace; náhrady Available at various institutes of the ASCR Stav předaných dat a úprava rozdělení vybraných měření 2017

Novák, Jakub; Jiřina jr., M.; Benešová, Michaela
Ústav informatiky, 2017