Generating Adaptive Behaviour within a Memory-Prediction Framework 英文参考文献.docVIP

下载本文档

8
0
约8.45万字
约 17页
2017-05-11 发布于上海
举报
版权申诉

Generating Adaptive Behaviour within a Memory-Prediction Framework 英文参考文献.doc

1、本文档共17页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
5、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
6、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
7、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
8、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Generating Adaptive Behaviour within a Memory-Prediction Framework 英文参考文献

GeneratingAdaptiveBehaviourwithinaMemory- PredictionFramework DavidRawlinson1*,GideonKowadlo2 1DepartmentofElectricalandElectronicEngineering,NationalICTAustralia,UniversityofMelbourne,Victoria,Australia,2OutwareMobilePty.Ltd.,Melbourne,Victoria, Australia Abstract TheMemory-PredictionFramework(MPF)anditsHierarchical-TemporalMemoryimplementation(HTM)havebeenwidely appliedtounsupervisedlearningproblems,forbothclassificationandprediction.Todate,therehasbeennoattemptto incorporateMPF/HTMinreinforcementlearningorotheradaptivesystems;thatis,touseknowledgeembodiedwithinthe hierarchy to control a system, or to generate behaviour for an agent. This problem is interesting because the human neocortex is believed to play a vital role in the generation of behaviour, and the MPF is a model of the human neocortex. We propose some simple and biologically-plausible enhancements to the Memory-Prediction Framework. Thesecauseittoexploreandinteractwithanexternalworld,whiletryingtomaximizeacontinuous,time-varyingreward function.AllbehaviourisgeneratedandcontrolledwithintheMPFhierarchy.Thehierarchydevelopsfromarandominitial configurationbyinteractionwiththeworldandreinforcementlearningonly.Amongotherdemonstrations,weshowthata 2-nodehierarchycanlearntosuccessfullyplay‘‘rocks,paper,scissors’’againstapredictableopponent. Citation: Rawlinson D, Kowadlo G (2012) Generating Adaptive Behaviour within a Memory-Prediction Framework. PLoS ONE 7(1): e29264. doi:10.1371/ journal.pone.0029264 Editor:EleniVasilaki,UniversityofSheffield,UnitedKingdom ReceivedJune2,2011;AcceptedNovember23,2011;PublishedJanuary17,2012 Copyright:?2012Rawlinson,Kowadlo.Thisisanopen-accessarticledistributedunderthetermsoftheCreativeCommonsAttributionLicense,whichpermits unrestricteduse,distribution,andreproductioninanymedium,providedtheoriginalauthorandsourcearecredited. Funding:Theauthorshavenosupportorfundingtoreport. CompetingInterests:DavidRawlinsonisemployedbyNationalICTAustralia(NICTA)attheVictorianResearchLaborato