developments and future directions of bio-inspired
10
ECOLOGICALINFORMATICS1(2006)9–22
obtainverydifferentfitnessvaluesindifferentpopulations.Coevolutionhasbeenstudiedextensivelyinrecentyearsasawaytodecomposingacomplexproblemautomatically(Dar-wenandYao,1997;Khareetal.,2004;Liuetal.,2001).Givenacomplexproblem,theideahereistousecoevolutiontoformspeciesautomatically,whereeachspeciesisspecialisedinsolvingonlypartsoftheentireproblem.Theentireproblemisthensolvedbycombiningalldifferentspeciestogether.Thiscanberegardedasanautomaticdivide-and-conquerapproachtocomplexproblemsolving.Wewillgiveoneexam-pleinoptimisationinthispapertoillustratehowproblemdecompositioncouldbebeneficial(Liuetal.,2001).
Anotherexampleofautomaticproblemdecompositionistheneuralnetworkensemblesthatwehaveproposed(Mon-irulIslametal.,2003;Liuetal.,2000;ChandraandYao,2004).Insteadofdesigningandtrainingamonolithicneuralnetworkforalargeandcomplexproblem,agroupofsim-plerneuralnetworkswereconstructedandtrained.Negativecorrelationandcoevolutionhavebeenusedtoincreasethediversitywithintheensembleofneuralnetworksandim-provethegeneralisationabilityoftheentireneuralnetworkensemble.Excellentresultshavebeenreportedintheliter-ature(MonirulIslametal.,2003;Liuetal.,2000;ChandraandYao,2004).
Theworkintroducedsofarcanberegardedastheapplica-tionofbio-inspiredapproaches(e.g.,evolutionarycomputa-tionandneuralnetworkensembles)toecoinformaticsproblems,wheretheinformationflowappearstobefromcomputationaltechniquestoproblemsrelatedtoecosystems.However,thereisanoppositedirectionofinformationflow,wheresomeideasandconceptsinbiologicalecosystemshaveinspiredresearcherstoexplorenewformsofcomputationandnewalgorithmsforproblemsolving.Thisisaveryimportantpartofecoinformaticsthatisunderexploredandunderstudiedatthemoment.Wehopeourpaperwillencouragemoreresearchersinmovingintothesenewresearchareas,whichrequireclosecollaborationbetweencomputerscientistsandecologists.
Therestofthispaperwillbeorganisedasfollows.Section2discussesourmodellingworkusingthetwostageevolution-aryapproaches(Lietal.,2004).Section3describesourworkoncoevolutionaryoptimisation(Liuetal.,2001).Section4pre-sentsneuralnetworkensemblesandnegativecorrelationlearning(ChandraandYao,2004).Section5outlinesthefutureresearchdirectionsforpossibleecosystem-inspiredcomputa-tionalmodelsandalgorithms.Finally,Section6concludesthepaperwithabriefsummary.
2.Data-drivenevolutionarymodelling
Therearemanyapproachesthatonecouldusefordata-drivenevolutionarymodelling(Lietal.,2002,2004).Wewillreviewoneexample(Lietal.,2004)herewheregeneticprogrammingwasusedtoevolvemodelstructures(i.e.,explicitfunctionforms)first.Thencommon“features”fromevolvedmodelswereidentifiedandabstracted.Finally,theabstractedmodelwascalibratedbyusingevolutionaryprogrammingtofine-tunemodelparameters.MoredetailsabouttheexamplecanbefoundinLietal.(2004).
2.1.Distributionoflightinellipticalgalaxies(Lietal.,
2004)
Inopticalimages,galaxieshaveawiderangeofshapesandsizes.Todevelopadeeperunderstandingoftheevolutionofgalaxies,itisimportanttoquantifytheirmorphologicalfea-turesasafirststageinanattempttolinkthemtothephysicsoftheirformation.
ThemostcommonlyusedfittingfunctionsforellipticalgalaxyprofilesaretheHubble'slawgivenbyIðrÞ¼
I0ðr=aþ1Þ;
ð1Þ
andthedeVaucouleursr1/4lawgivenbyIðrÞ¼IeexpfÀ3:33½ðr=reÞ1=4À1 g:
ð2Þ
Eachfunctionhastwoparameters,abrightnessscaleI0orIeandasizescaleaorre.I0isthesurfacebrightnessatr=0,i.e.,thecentralsurfacebrightness.Thescalelengthaisthedis-tanceatwhichthesurfacebrightnessfallstoaquarterofitscentralvalue.Incontrast,re,knownastheeffectiveradius,containshalfofthetotallightofthegalaxy,andIeisthebrightnessatre.Thetwolawsgiveareasonablygooddescrip-tionoftheluminosityprofilesofellipticalgalaxiesandthebulgesofsometypesofspiralgalaxies.However,theydonotdescribewelltheseprofilesbeyondcertainboundsofrorthebulgesofspiralgalaxieswithpronouncedspiralfeatures.Forthelatter,apopularmodelisanexponentialformIðrÞ¼5:36Ieexp½À1:68ðr=reÞ :
ð3Þ
NeitherEq.(2)norEq.(3)hasbeenformallylinkedtoaphysicalmodelofgalaxyformation,andtheyremainmereempiricalfitstoobservedprofiles.Hubble'smodel(1)isnotaverygoodfittoawiderangeofobservedellipticals,butisrelatedtopossibledensityprofilesofself-gravitatingisother-malspheresofgas.Itwouldbedesirabletohaveasinglemodelthatwoulddescribeallellipticalgalaxieswithavaria-tionofparameters,especiallyifthismodelcouldbelinkedwiththephysicsofcollapsinggascloudsandtheformationofself-gravitatingellipsoidalsystems.
Therehasbeenalotofeffortintheliteraturetofindap-propriatemathematicalfunctionstodescribeawiderangeofprofilesofvariouscomponentsofspiralandellipticalgalaxies,andtofindplausiblevaluesforparametersthatwouldfitobservedprofiles.Bothtasksarenon-trivial.Theusualap-proachistopostulateamathematicalmodelcomprisingofcommonmathematicalfunctions,thentoapplyfittingalgo-rithmstofindsuitableparametersforthesefunctions.Theparameterfittingalgorithmusuallyadoptedisthenon-linearreducedχ2minimisationgivenbyv2¼
1X½ImodelðiÞÀIobsðiÞ 2
m;
ð4Þ
idwhereIobs(i)istheindividualobservedprofilevalue,Imodel(i)isthevaluecalculatedfromthefittingfunction,νisthenumberofdegreesoffreedom,andδisthestandarddeviationofthedata.Onedisadvantageofnon-linearminimisationalgo-rithmsistheirsensitivitytotheinitialvaluesprovided.
Global optimisation Evol... 暂无评价 14页 免费 Neural Networks – algor.....Combining Evolutionary Algorithms and Neural NetworksCombining Evolutionary Algorithms...
global optimisation using evolutionary and hybrid algorithms constraint handling ...neural networks and evolutionary algorithms data mining other interests I have...
programming, global optimisation, evolutionary learning, neural networks, ...(also known as strategy parameters in self-adaptive evolutionary algorithms)....
Algorithm Using an Inverse Neural Network Ant? nio...2 MULTIOBJECTIVE OPTIMISATION ALGORITHM The ...Evolutionary Algorithms to explore and discover ...
Optimisation of Density Estimation Models with Evolutionary Algorithms Abstract. ...We employ a hybrid method consisting of an evolutionary algorithm for struc...
Global optimisation by e... 暂无评价 10页 免费 Constrained multiobjecti......Global optimization by means of evolutionary algorithms Evolution Strategies (ESs...
Evolutionary Many-Objective Optimisation An Exploratory Analysis Abstract – This inquiry explores the effectiveness of a class of modern evolutionary algorithms,...
ed particle swarm optimisation to train the ...1998. Evolutionary approaches to neural control in...1998. Evolutionary algorithms and gradient search: ...
Evolutionary Algorithms Most work in evolutionary ...cult optimisation problems, the theoretical results ...neural network ensembles, global optimization, computation...
热门文档