"information geometry; multidimensional distributions; information divergence; exponential families; generalized maximum likelihood estimators; conditional independence; inference mechanisms; uncertainty calculi; entropy functions; polymatroids"@en . "0"^^ . "Tento projekt se zab\u00FDval informa\u010Dn\u00ED geometri\u00ED mnohorozm\u011Brn\u00FDch model\u016F statistiky a um\u011Bl\u00E9 inteligence. Hlavn\u00ED v\u00FDsledky p\u0159isp\u00EDvaj\u00ED k teorii exponenci\u00E1ln\u00EDch rodin a entropick\u00FDch funkc\u00ED."@cs . . "0"^^ . . "2010-12-31+01:00"^^ . " information divergence" . . "2006-01-01+01:00"^^ . " entropy functions" . . . " inference mechanisms" . " uncertainty calculi" . . "Information geomerty of multidimensional models in statistics and artificial intelligence."@en . . . . . . "http://www.isvav.cz/projectDetail.do?rowId=IAA100750603"^^ . "information geometry" . "2010-03-09+01:00"^^ . . . . "24"^^ . "IAA100750603" . " generalized maximum likelihood estimators" . "24"^^ . . " multidimensional distributions" . " conditional independence" . "2013-06-28+02:00"^^ . . . "The project investigated information geometry of multidimensional models of statistics and artificial intelligence. Main results contribute to the theory of exponential families and entropic functions."@en . "Multidimensional and highly-structured distributions underpin a number models in statistics and artificial intelligence with broad applications. Their theoretical background includes modern methods of statistics and calculi of uncertainty, involving the information geomerty as well. The goal of this project is investigation and development of geometrical approaches to these mathematical models, in particular, of the theory of exponential families, with applications in self-learning systems, and the theory of multidimensional models based on qualitative knowledge like conditional independence, graphically specified dependencies and symmetry. Expected theoretical results should enrich areas of the probability theory, statistics, calculi of uncertainty, theory of information and complexity, and open new application horizons in artificial intelligence."@en . . . . " exponential families" . "1"^^ . "Mnohorozm\u011Brn\u00E9 a vysoce strukturovan\u00E9 distribuce jsou z\u00E1kladem \u0159ady prakticky pou\u017E\u00EDvan\u00FDch model\u016F statistiky a um\u011Bl\u00E9 inteligence. Jejich teoretick\u00FDm z\u00E1kladem jsou dnes ji\u017E hluboce rozvinut\u00E9 a nepostradateln\u00E9 kalkuly pro popis neur\u010Ditosti zahrnuj\u00EDc\u00ED tak\u00E9 informa\u010Dn\u00ED geometrii. C\u00EDlem tohoto projektu je dal\u0161\u00ED rozv\u00EDjen\u00ED geometrick\u00E9ho p\u0159\u00EDstupu k t\u011Bmto matematick\u00FDm model\u016Fm a to zejm\u00E9na teorie exponenci\u00E1ln\u00EDch rodin, jej\u00ED aplikace v samoorganizuj\u00EDc\u00EDch se syst\u00E9mech, a teorie mnohorozm\u011Brn\u00FDch model\u016F budovan\u00FDch na kvalitativn\u00ED expertn\u00ED informaci, jakou je podm\u00EDn\u011Bn\u00E1 nez\u00E1vislost, graficky specifikovan\u00E9 souvislosti a symetrie. O\u010Dek\u00E1van\u00E9 teoretick\u00E9 v\u00FDsledky by m\u011Bly obohatit oblasti teorie pravd\u011Bpodobnosti, statistiky, kalkul\u016F neur\u010Ditosti, teorie informace a komplexity, a otev\u0159\u00EDt nov\u00E9 aplika\u010Dn\u00ED mo\u017Enosti v um\u011Bl\u00E9 inteligenci." . "Informa\u010Dn\u00ED geometrie mnohorozm\u011Brn\u00FDch model\u016F statistiky a um\u011Bl\u00E9 inteligence." .