keywords:"cross-entropy" - Výsledky hledání - Digitální repozitář

host :: přihlásit Digitální repozitář
		Hledej		Nový záznam		Nápověda		O repozitáři

Hlavní stránka > Výsledky hledání: keywords:"cross-entropy"

Hledej:

Tipy pro vyhledávaní :: Rozšířené hledání

Hledej ve sbírkách:

Seřadit podle:	Zobrazit výsledky:	Výstupní formát:

	Mining of Textual Data from the Web for Speech Recognition Kubalík, Jakub ; Plchot, Oldřich (oponent) ; Mikolov, Tomáš (vedoucí práce) The preliminary goals of this project were to get familiar with language modeling for speech recognition and techniques for acquisition of text data from the Web. Speech recognition techniques are introduced and statistical language modeling is described in detail. The text also covers mining models and techniques, information retrieval especially. Specific problems of Web mining are discussed and Google search is introduced. Special attention was paid to detailed description of implementation of the text mining system. However, the main goal of this work was to determine, whether the data acquired from the Web can provide some improvement into the recognition systems. The text is describing experiments, which use the retrieved Web data to update sample language models. Úplný záznam
	Mining of Textual Data from the Web for Speech Recognition Kubalík, Jakub ; Plchot, Oldřich (oponent) ; Mikolov, Tomáš (vedoucí práce) The preliminary goals of this project were to get familiar with language modeling for speech recognition and techniques for acquisition of text data from the Web. Speech recognition techniques are introduced and statistical language modeling is described in detail. The text also covers mining models and techniques, information retrieval especially. Specific problems of Web mining are discussed and Google search is introduced. Special attention was paid to detailed description of implementation of the text mining system. However, the main goal of this work was to determine, whether the data acquired from the Web can provide some improvement into the recognition systems. The text is describing experiments, which use the retrieved Web data to update sample language models. Úplný záznam
	Evaluation of Kullback-Leibler Divergence Homolová, Jitka ; Kárný, Miroslav Kullback-Leibler divergence is a leading measure of similarity or dissimilarity of probability distributions. This technical paper collects its analytical and numerical expressions for the broad range of distributions. Úplný záznam

Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.

Digitální repozitář :: :: :: ::
Powered by v1.1.2
Spravuje

Tato stránka je dostupná také v následujících jazycích:
Česky English