자료유형 | 학위논문 |
---|---|
서명/저자사항 | Latent Representation and Sampling in Network: Application in Text Mining and Biology. |
개인저자 | Saha, Tanay Kumar. |
단체저자명 | Purdue University. Computer Sciences. |
발행사항 | [S.l.]: Purdue University., 2018. |
발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2018. |
형태사항 | 291 p. |
기본자료 저록 | Dissertation Abstracts International 79-12B(E). Dissertation Abstract International |
ISBN | 9780438154506 |
학위논문주기 | Thesis (Ph.D.)--Purdue University, 2018. |
일반주기 |
Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.
Advisers: Mohammad Al Hasan |
요약 | In classical machine learning, hand-designed features are used for learning a mapping from raw data. However, human involvement in feature design makes the process expensive. Representation learning aims to learn abstract features directly from |
요약 | In this dissertation, we propose models for incorporating temporal information given as a collection of networks from subsequent time-stamps. The primary objective of our models is to learn a better abstract feature representation of nodes and e |
요약 | Besides applying to the network data, we also employ our models to incorporate extra-sentential information in the text domain for learning better representation of sentences. We build a context network of sentences to capture extra-sentential |
요약 | A problem with the abstract features that we learn is that they lack interpretability. In real-life applications on network data, for some tasks, it is crucial to learn interpretable features in the form of graphical structures. For this we need |
요약 | Finally, we show that we can use these frequent subgraph statistics and structures as features in various real-life applications. We show one application in biology and another in security. In both cases, we show that the structures and their st |
일반주제명 | Computer science. Artificial intelligence. Information science. |
언어 | 영어 |
바로가기 |
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |