<?xml version="1.0" encoding="utf-8"?>
<?xml-stylesheet type="text/xsl" href="style/detail_T.xsl"?>
<bibitem type="C">   <ARLID>0411379</ARLID> <utime>20240111140636.5</utime><mtime>20060210235959.9</mtime>        <title language="eng" primary="1">Eficient variant of algorithm FastICA for independent component analysis attaining the Cramér-Rao lower bound</title>  <publisher> <place>Paris</place> <name>Telecom Paris</name> <pub_time>2005</pub_time> </publisher> <specification> <page_count>6 s.</page_count> <media_type>CD-ROM</media_type> </specification>   <serial><title>Proceedings of IEEE/SP 13th Workshop on Statistical Signal Processing</title><part_num/><part_title/><page_num>7-12</page_num></serial>   <title language="cze" primary="0">Asymptoticky eficientní varianta algoritmu FastICA pro analýzu nezávislých komponent</title>    <keyword>blind signal separation</keyword>   <keyword>linear mixture</keyword>    <author primary="1"> <ARLID>cav_un_auth*0108100</ARLID> <name1>Koldovský</name1> <name2>Zbyněk</name2> <institution>UTIA-B</institution> <full_dept>Department of Stochastic Informatics</full_dept>  <fullinstit>Ústav teorie informace a automatizace AV ČR, v. v. i.</fullinstit> </author> <author primary="0"> <ARLID>cav_un_auth*0101212</ARLID> <name1>Tichavský</name1> <name2>Petr</name2> <institution>UTIA-B</institution> <full_dept>Department of Stochastic Informatics</full_dept>  <fullinstit>Ústav teorie informace a automatizace AV ČR, v. v. i.</fullinstit> </author>   <source> <source_size>206 kB</source_size> </source>     <COSATI>12B</COSATI>    <cas_special> <project> <project_id>1M0572</project_id> <agency>GA MŠk</agency> <ARLID>cav_un_auth*0001814</ARLID> </project> <research> <research_id>CEZ:AV0Z10750506</research_id> </research>  <abstract language="eng" primary="1">An improved version of algorithm FastICA is proposed which is asymptotically eficient,. i.e. its accuracy attains the corresponding Cramer-Rao lower bound provided that the probability distribution of the to be separated signals belongs to class of generalized Gaussian distributions. Its computational complexity is about three times greater than that of ordinary symmetric FastICA. In simulations the proposed method is compared with JADE and with non-parametric ICA.</abstract> <abstract language="cze" primary="0">V práci je navržena nová varianta algoritmu FastICA, která je asymptoticky eficientní, tj. její přesnost se blíží Rao-Cramerově hranici, za předpokladu že pravděpodobnostní rozložení separovaných signálů je z třídy zobecněných Gaussovských distribucí. V simulacích je navržená metoda porovnávána se známým algoritmem JADE a s neparametrickou ICA.</abstract>  <action target="WRD"> <ARLID>cav_un_auth*0213221</ARLID> <name>IEEE/SP Workshop on Statistical Signal Processing /13./</name> <place>Bordeaux</place> <country>FR</country> <dates>17.07.2005-20.07.2005</dates>  </action>     <RIV>BB</RIV> <reportyear>2006</reportyear>   <department>SI</department>    <permalink>http://hdl.handle.net/11104/0131461</permalink>    <ID_orig>UTIA-B 20050109</ID_orig>    <arlyear>2005</arlyear>       <unknown tag="mrcbU10"> 2005 </unknown> <unknown tag="mrcbU10"> Paris Telecom Paris </unknown> <unknown tag="mrcbU56"> 206 kB </unknown> <unknown tag="mrcbU63"> Proceedings of IEEE/SP 13th Workshop on Statistical Signal Processing 7 12 </unknown> </cas_special> </bibitem>