卷积神经网络和一些独立成分分析的外文文献
doc.guandang.net
Invitedarticle
Independentcomponentanalysis:algorithmsandapplications
¨rinen,E.Oja*A.Hyva
NeuralNetworksResearchCentre,HelsinkiUniversityofTechnology,P.O.Box5400,FIN-02015HUT,Helsinki,Finland
Received28March2000;accepted28March2000
Abstract
Afundamentalprobleminneuralnetworkresearch,aswellasinmanyotherdisciplines,is ndingasuitablerepresentationofmultivariate
data,i.e.randomvectors.Forreasonsofcomputationalandconceptualsimplicity,therepresentationisoftensoughtasalineartransformationoftheoriginaldata.Inotherwords,eachcomponentoftherepresentationisalinearcombinationoftheoriginalvariables.Well-knownlineartransformationmethodsincludeprincipalcomponentanalysis,factoranalysis,andprojectionpursuit.Independentcomponentanalysis(ICA)isarecentlydevelopedmethodinwhichthegoalisto ndalinearrepresentationofnon-Gaussiandatasothatthecomponentsarestatisticallyindependent,orasindependentaspossible.Sucharepresentationseemstocapturetheessentialstructureofthedatainmanyapplications,includingfeatureextractionandsignalseparation.Inthispaper,wepresentthebasictheoryandapplicationsofICA,andourrecentworkonthesubject. 2000PublishedbyElsevierScienceLtd.
Keywords:Independentcomponentanalysis;Projectionpursuit;Blindsignalseparation;Sourceseparation;Factoranalysis;Representation
1.Motivation
Imaginethatyouareinaroomwheretwopeoplearespeakingsimultaneously.Youhavetwomicrophones,whichyouholdindifferentlocations.Themicrophonesgiveyoutworecordedtimesignals,whichwecoulddenotebyx1(t)andx2(t),withx1andx2theamplitudes,andtthetimeindex.Eachoftheserecordedsignalsisaweightedsumofthespeechsignalsemittedbythetwospeakers,whichwedenotebys1(t)ands2(t).Wecouldexpressthisasalinearequation:
x1 t a11s1 a12s2x2 t a21s1 a22s2
1 2
wherea11,a12,a21,anda22aresomeparametersthatdependonthedistancesofthemicrophonesfromthespeakers.Itwouldbeveryusefulifyoucouldnowestimatethetwooriginalspeechsignalss1(t)ands2(t),usingonlytherecordedsignalsx1(t)andx2(t).Thisiscalledthecocktail-partyproblem.Forthetimebeing,weomitanytimedelaysorotherextrafactorsfromoursimpli edmixingmodel.Asanillustration,considerthewaveformsinFigs.1and2.Theseare,ofcourse,notrealisticspeechsignals,butsuf ceforthisillustration.Theoriginalspeechsignals
*Correspondingauthor.Tel.: 358-9-4513265;fax: 358-9-4513277.
¨rinen),erkki.oja@E-mailaddresses:aapo.hyvarinen@hut. (A.Hyva
hut. (E.Oja).
0893-6080/00/$-seefrontmatter 2000PublishedbyElsevierScienceLtd.PII:S0893-6080(00)00026-5
couldlooksomethinglikethoseinFig.1andthemixedsignalscouldlooklikethoseinFig.2.TheproblemistorecoverthedatainFig.1usingonlythedatainFig.2.Actually,ifweknewtheparametersaij,wecouldsolvethelinearequationin(1)byclassicalmethods.Thepointis,however,thatifyoudonotknowtheaij,theproblemisconsiderablymoredif cult.
Oneapproachtosolvingthisproblemwouldbetousesomeinformationonthestatisticalpropertiesofthesignalssi(t)toestimatetheaii.Actually,andperhapssurprisingly,itturnsoutthatitisenoughtoassumethats1(t)ands2(t),ateachtimeinstantt,arestatisticallyindependent.Thisisnotanunrealisticassumptioninmanycases,anditneednotbeexactlytrueinpractice.TherecentlydevelopedtechniqueofIndependentComponentAnalysis,orICA,canbeusedtoestimatetheaijbasedontheinformationoftheirindepen-dence,whichallowsustoseparatethetwooriginalsourcesignalss1(t)ands2(t)fromtheirmixturesx1(t)andx2(t).Fig.3givesthetwosignalsestimatedbytheICAmethod.Ascanbeseen,theseareveryclosetotheoriginalsourcesignals(theirsignsarereversed,butthishasnosigni cance).
Independentcomponentanalysiswasoriginallydevel-opedtodealwithproblemsthatarecloselyrelatedtothecocktail-partyproblem.SincetherecentincreaseofinterestinICA,ithasbecomeclearthatthisprinciplehasalotofotherinterestingapplicationsaswell.
Consider,forexample,electricalrecordingsofbrainactivityasgivenbyanelectroencephalogram(EEG).TheEEGdataconsistsofrecordingsofelectricalpotentialsin


独立成分分析Independent+Component+Analysis+Algorithms+and+Applications_IT/... A comparative analysis... 18页 免费 Chapter 2 Independent ... 16页 ...
Independent Component Analysis: Algorithms and Applications E. Oja1 1 Helsinki University of Technology, Department of Computer Science and Engineering, P.O....
Independent Component Analysis algorithms and applications 暂无评价0人阅读0次下载举报文档 ICA 著名参考文献 下载此文档 大小:17.00MB 1财富值 收藏此文档...
《Independent 上面介绍的内容基本上是讲义上的 Independent Component Analysis: Algorithms and Applications Applications》(AapoHyv?rinen and ErkkiOja AapoHyv?rinen ...
独立成分分析 Independent Component Analysis (ICA)齐娟 2007-5-29 主要内容 ?...论文: Independent component analysis: algorithms and applications Survey on ...
Independent Component Analysis: Algorithms and Applications April 1999 1 Motivation Imagine that you are in a room where two people are speaking simultaneously...
Fast and robust fixed-point algorithms for independent component analysis ...Two promising applications of ICA are blind source separation and feature ...
Independent Component Analysis独立成分分析 PPT_理学_高等教育_教育专区。...… and most applications where Factor Analysis and PCA is currently used. ...
In ordinary independent component analysis, the components are assumed to be...In practical applications of ICA, however, one can very often observe clear...
独Independent Component Analysis (ICA)齐娟 2007-5-29 主要内容 ? ? ? ?...论: Independent component analysis: algorithms and applications Survey on ...
热门文档