a learning algorithm for boltzmann machines 1985 3542外语英文电子书

a learning algorithm for boltzmann machines 1985 3542外语英文电子书

ID:8006287

大小:1.80 MB

页数:23页

时间:2018-03-04

a learning algorithm for boltzmann machines 1985 3542外语英文电子书_第1页
a learning algorithm for boltzmann machines 1985 3542外语英文电子书_第2页
a learning algorithm for boltzmann machines 1985 3542外语英文电子书_第3页
a learning algorithm for boltzmann machines 1985 3542外语英文电子书_第4页
a learning algorithm for boltzmann machines 1985 3542外语英文电子书_第5页
资源描述:

《a learning algorithm for boltzmann machines 1985 3542外语英文电子书》由会员上传分享,免费在线阅读,更多相关内容在教育资源-天天文库

1、COGNITIVESCIENCE9,147-169(1985)ALearningAlgorithmforBoltzmannMachines*DAVIDH.ACKLEYGEOFFREYE.HINTONComputerScienceDepartmentCarnegie-MellonUniversityTERRENCEJ.SEJNOWSKIBiophysicsDepartmentTheJohnsHopkinsUniversityThecomputotionolpowerofmassivelyparallelnetworksofsi

2、mpleprocessingelementsresidesinthecommunicationbandwidthprovidedbythehardwareconnectionsbetweenelements.Theseconnectionsconallowasignificantfractionoftheknowledgeofthesystemtobeappliedtoaninstanceofaprob-leminoveryshorttime.Onekindofcomputationforwhichmassivelyporo

3、llelnetworksappeartobewellsuitedislargeconstraintsatisfactionsearches,buttousetheconnectionsefficientlytwoconditionsmustbemet:First,asearchtechniquethatissuitableforparallelnetworksmustbefound.Second,theremustbesomewayofchoosinginternalrepresentationswhichallowthep

4、reexistinghardwareconnectionstobeusedefficientlyforencodingthecon-straintsinthedomainbeingsearched.Wedescribeagenerolparallelsearchmethod,basedonstatisticalmechanics,andweshowhowitleadstoagen-erallearningruleformodifyingtheconnectionstrengthssoastoincorporateknowle

5、dgeoboutotaskdomaininonefficientway.Wedescribesomesimpleexamplesinwhichthelearningalgorithmcreatesinternalrepresentationsthotoredemonstroblythemostefficientwayofusingthepreexistingconnec-tivitystructure.1.INTRODUCTIONEvidenceaboutthearchitectureofthebrainandthepote

6、ntialofthenewVLSItechnologyhaveledtoaresurgenceofinterestin“connectionist”sys-lTheresearchreportedherewassupportedbygrantsfromtheSystemDevelopmentFoundation.WethankPeterBrown,FrancisCrick,MarkDerthick,ScottFahlman,JerryFeldman,StuartGeman,GailGong,JohnHopfield,JayM

7、cClelland,BarakPearlmutter,HarryPrintz,DaveRumelhart,TimShallice,PaulSmolensky,RickSzeliski,andVenkatara-manVenkatasubramanianforhelpfuldiscussions.ReprintrequestsshouldbeaddressedtoDavidAckley,ComputerScienceDepartment,Carnegie-MellonUniversity,Pittsburgh,PA15213.

8、147148ACKLEY.HINTON.ANDSEJNOWSKIterns(Feldman&Ballard,1982;Hinton&Anderson,1981)thatstoretheirlong-termknowledgeasthestrengthsoftheconnectionsbet

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。