Joint active feature acquisition and classification with variable-size set encoding가변 크기 집합의 인코딩을 이용한 동적 피쳐 획득과 분류의 공동 학습

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 414
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorYang, Eunho-
dc.contributor.advisor양은호-
dc.contributor.authorShim, Hajin-
dc.date.accessioned2019-09-04T02:47:00Z-
dc.date.available2019-09-04T02:47:00Z-
dc.date.issued2019-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=843528&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/267058-
dc.description학위논문(석사) - 한국과학기술원 : 전산학부, 2019.2,[iii, 23 p. :]-
dc.description.abstractWe consider the problem of active feature acquisition where the goal is to sequentially select the subset of features in order to achieve the maximum prediction performance in the most cost-effective way at test time. In this work, we formulate this active feature acquisition as a joint learning problem of training both the classifier (environment) and the reinforcement learning (RL) agent that decides either to ‘stop and predict’ or ‘collect a new feature’ at test time, in a cost-sensitive manner. We also introduce a novel encoding scheme to represent acquired subsets of features by proposing an order-invariant set encoding at the feature level, which also significantly reduces the search space for our agent. We evaluate our model on a carefully designed synthetic dataset for the active feature acquisition as well as several medical datasets. Our framework shows meaningful feature acquisition process for diagnosis that complies with human knowledge, and outperforms all baselines in terms of prediction performance as well as feature acquisition cost.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectActive feature acquisition▼areinforcement learning▼ajoint learning▼avariable-size set encoding-
dc.subject능동적 피쳐 획득▼a강화학습▼a공동 학습▼a가변 크기 집합 인코딩-
dc.titleJoint active feature acquisition and classification with variable-size set encoding-
dc.title.alternative가변 크기 집합의 인코딩을 이용한 동적 피쳐 획득과 분류의 공동 학습-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :전산학부,-
dc.contributor.alternativeauthor심하진-
Appears in Collection
CS-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0