<?xml version="1.0" encoding="utf-8"?>
<?xml-stylesheet type="text/xsl" href="style/detail_T.xsl"?>
<bibitem type="C">   <ARLID>0041688</ARLID> <utime>20240111140639.5</utime><mtime>20061003235959.9</mtime>         <title language="eng" primary="1">The Restricted Variational Bayes Approximation in Bayesian Filtering</title>  <specification> <page_count>4 s.</page_count> <media_type>CD-ROM</media_type> </specification>   <serial><ARLID>cav_un_epca*0076872</ARLID><ISBN>978-1-4244-0579-4</ISBN><title>Proceedings of the NSSPW'06 Workshop</title><part_num/><part_title/><page_num>1-4</page_num><publisher><place>Cambridge</place><name>University of Cambridge</name><year>2006</year></publisher></serial>   <title language="cze" primary="0">Použití aproximace Variační Bayes v sekvenčním odhadování</title>    <keyword>Bayesian filtering</keyword>   <keyword>Variational Bayes</keyword>   <keyword>particle filters</keyword>    <author primary="1"> <ARLID>cav_un_auth*0101207</ARLID> <name1>Šmídl</name1> <name2>Václav</name2> <institution>UTIA-B</institution> <full_dept>Department of Adaptive Systems</full_dept>  <fullinstit>Ústav teorie informace a automatizace AV ČR, v. v. i.</fullinstit> </author> <author primary="0"> <ARLID>cav_un_auth*0021112</ARLID> <name1>Quinn</name1> <name2>A.</name2> <country>IE</country>  </author>   <source> <source_type>textový soubor</source_type> </source>     <COSATI>09I</COSATI> <COSATI>09J</COSATI>    <cas_special> <project> <project_id>1M0572</project_id> <agency>GA MŠk</agency> <ARLID>cav_un_auth*0001814</ARLID> </project> <project> <project_id>1ET100750401</project_id> <agency>GA AV ČR</agency> <ARLID>cav_un_auth*0001792</ARLID> </project> <research> <research_id>CEZ:AV0Z10750506</research_id> </research>  <abstract language="eng" primary="1">The Variational Bayes (VB) approach is used as a one-step approximation for Bayesian ﬁltering. It requires the availability of moments of the free-form distributional optimizers. The latter may have intractable functional forms. In this contribution, we replace these by appropriate ﬁxed-form distributions yielding the required moments. We address two scenarios of this Restricted VB (RVB) approximation. For the ﬁrst scenario, an application in identiﬁcation of HMMs is given. Close relationship of the second scenario to Rao-Blackwellized particle ﬁltering is discussed and their performance is illustrated on a simple non-linear model.</abstract> <abstract language="cze" primary="0">Použití variační aproximace v Bayesovské filtraci je možné pouze pokud jsou spočitatelné momenty optimálních distribucí. V mnoha případech však tyto distribuce mají komplikovanou formu a jejich momenty nejsou známy analyticky. V tomto příspěvku navrhujeme nahradit momenty optimální distribuce momenty vhodně zvolené blízké distribuce. Postup je ilustrován na dvou konkrétních příkladech. První se týká identifikace HMM modelů a druhý urychlením marginalizovaných particle filtrů.</abstract>  <action target="WRD"> <ARLID>cav_un_auth*0217487</ARLID> <name>Non-linear Statistical Signal Processing Workshop</name> <place>Cambridge</place> <dates>13.09.2006-15.09.2006</dates>  <country>GB</country> </action>    <reportyear>2010</reportyear>  <RIV>BC</RIV>      <permalink>http://hdl.handle.net/11104/0135082</permalink>       <arlyear>2006</arlyear>       <unknown tag="mrcbU56"> textový soubor </unknown> <unknown tag="mrcbU63"> cav_un_epca*0076872 Proceedings of the NSSPW'06 Workshop 978-1-4244-0579-4 1 4 Cambridge University of Cambridge 2006 </unknown> </cas_special> </bibitem>