返回
presenting some machine-learning methods-introducing differential evolution

presenting some machine-learning methods-introducing differential evolution

ID：7296121

大小：433.53 KB

页数：35页

时间：2018-02-10

presenting some machine-learning methods-introducing differential evolution_第1页
presenting some machine-learning methods-introducing differential evolution_第2页
presenting some machine-learning methods-introducing differential evolution_第3页
presenting some machine-learning methods-introducing differential evolution_第4页
presenting some machine-learning methods-introducing differential evolution_第5页
资源描述：

《presenting some machine-learning methods-introducing differential evolution》由会员上传分享，免费在线阅读，更多相关内容在工程资料-天天文库。

1、Chapter13Presentingsomemachine-learningmethodsMachinelearningisaboutprogrammingcomputerstolearnandtoimproveautomaticallywithexperience.Whilecomputerscannotyetlearnaswellaspeople,algorithmshavebeendevisedthatareeffectiveforcertaintypesoflearningtasks,andatheoreticalunderstandingoflearnin

2、ghasemerged.Computerprogramsdeveloped,exhibitingusefultypesoflearning,especiallyinspeechrecognitionanddatamining(seeMitchell[1997]).Machinelearningisinherentlyamultidisciplinaryfielddrawingresultsfromartificialintelligence,probabilityandstatistics,computationalcomplexitytheory,controltheo

3、ry,informationtheory,philosophy,psychology,neurobiology,andotherfields.Wearegoingtointroducesomeofthesefieldsastheyhavebeenextensivelyusedinthefinancialindustrytodevisesystematictradingstrategies.13.1Somefactsonmachine-learning13.1.1IntroductiontodataminingTherapidgrowthandintegrationofdat

4、abasesprovidedscientists,engineers,andbusinesspeoplewithavastnewresourcethatcanbeanalysedtomakescientificdiscoveries,optimiseindustrialsystems,anduncoverfinanciallyvaluablepatterns.Newmethodstargetedatlargedataminingproblemshavebeendeveloped.DataMining(DM)istheanalysisof(large)observation

5、aldatasetstofindunsuspectedrelationshipsandtosummarisethedatainnovelwaysthatarebothunderstandableandusefultothedataowner(seeHandetal.[2001]).ThereexistsseveralfunctionalitiestoDM,suchthatdatacharacterisationsummarisingthegeneralcharacteristicsorfeaturesofatargetclassofdata,anddatadiscrim

6、inationcomparingthegeneralfeaturesoftargetclassdataobjectswiththegeneralfeaturesofobjectsfromasetofcontrastingclasses.Further,associationanalysisisthediscoveryofassociationrulesshowingattributevalueconditionsoccurringfrequentlytogetherinagivensetofdata.Classificationistheprocessoffindinga

7、setofmodels(orfunctions)thatdescribeanddistinguishdataclassesorconcepts,forthepurposeofbeingabletousethemodeltopredicttheclassofobjectswhoseclasslabelisunknown.Machinelearninghavebeentraditionallyusedforclassification,wheremodelssuchasdecisiontrees,SVM,neuralnetworks,Bayesianbel

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。