GUEST EDITORIAL Genetic Algorithms and Machine Learning

GUEST EDITORIAL Genetic Algorithms and Machine Learning

ID:39771855

大小:333.12 KB

页数:5页

时间:2019-07-11

GUEST EDITORIAL Genetic Algorithms and Machine Learning_第1页
GUEST EDITORIAL Genetic Algorithms and Machine Learning_第2页
GUEST EDITORIAL Genetic Algorithms and Machine Learning_第3页
GUEST EDITORIAL Genetic Algorithms and Machine Learning_第4页
GUEST EDITORIAL Genetic Algorithms and Machine Learning_第5页
资源描述:

《GUEST EDITORIAL Genetic Algorithms and Machine Learning》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、MachineLearning3:95-99,1988©1988KluwerAcademicPublishers-ManufacturedinTheNetherlandsGUESTEDITORIALGeneticAlgorithmsandMachineLearningMetaphorsforlearningThereisnoapriorireasonwhymachinelearningmustborrowfromnature.Afieldcouldexist,completewithwell-definedalgorithms,datastructures,andtheoriesoflear

2、ning,withoutoncereferringtoorganisms,cognitiveorgeneticstructures,andpsychologicalorevolutionarytheories.Yetattheendoftheday,withthepositionpaperswritten,thecomputerspluggedin,andtheprogramsdebugged,alearningedificedevoidofnaturalmetaphorwouldlacksomething.Itwouldignorethefactthatallthesecreationsh

3、avebecomepossibleonlyafterthreebillionyearsofevolutiononthisplanet.ItwouldmissthepointthattheveryideasofadaptationandlearningareconceptsinventedbythemostrecentrepresentativesofthespeciesHomosapiensfromthecarefulobservationofthemselvesandlifearoundthem.Itwouldmissthepointthatnaturalexamplesoflearnin

4、gandadaptationaretreasuretrovesofrobustproceduresandstructures.Fortunately,thefieldofmachinelearningdoesrelyuponnature'sbountyforbothinspirationandmechanism.Manymachinelearningsystemsnowborrowheavilyfromcurrentthinkingincognitivescience,andrekindledin-terestinneuralnetworksandconnectionismisevidenc

5、eofseriousmechanisticandphilosophicalcurrentsrunningthroughthefield.Anotherareawherenat-uralexamplehasbeentappedisinworkongeneticalgorithms(GAs)andgenetics-basedmachinelearning.Rootedintheearlycyberneticsmovement(Holland,1962),progresshasbeenmadeinboththeory(Holland,1975;Hol-land,Holyoak,Nisbett,&T

6、hagard,1986)andapplication(Goldberg,1989;Grefenstette,1985,1987)tothepointwheregenetics-basedsystemsarefind-ingtheirwayintoeverydaycommercialuse(Davis&Coombs,1987;Fourman,1985).GeneticalgorithmsandclassifiersystemsThisspecialdoubleissueofMachineLearningisdevotedtopapersconcern-inggeneticalgorithmsa

7、ndgenetics-basedlearningsystems.Simplystated,geneticalgorithmsareprobabilisticsearchproceduresdesignedtoworkonlargespacesinvolvingstatesthatcanberepresentedbystrings.Thesemeth-odsareinherentlyparallel,using

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。