Progressive transmission and inference of deep learning models served over network네트워크를 통해 제공되는 딥 러닝 모델의 점진적 전송 및 추론

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 83
  • Download : 0
Modern image files support progressive transmission mode and provide a preview before downloading the entire image for improved user experience to cope with a slow network connection. In this paper, with a similar goal, we propose a progressive transmission framework for large sized deep learning models, especially to deal with the scenario where pre-trained deep learning models are transmitted from servers and executed at user devices. Our progressive transmission framework allows inferring approximate models in the middle of file delivery, and quickly provide an acceptable intermediate outputs. On the server-side, a deep learning model is divided and progressively transmitted to the user devices. Then, the divided pieces are progressively concatenated to construct approximate models on user devices. Experiments show that our method is computationally efficient without increasing the model size and total transmission time while preserving the model accuracy. We further demonstrate that our method can improve the user experience by providing the approximate models especially in a slow connection.
Advisors
Choi, Sungheeresearcher최성희researcher
Description
한국과학기술원 :전산학부,
Publisher
한국과학기술원
Issue Date
2021
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전산학부, 2021.8,[iii, 19 p. :]

Keywords

Deep learning model transmission▼aDeep learning model deployment▼aUser experience▼aProgressive transmission; 점진적 전송▼a딥 러닝 모델▼a점진적 추론▼a네트워크▼a사용자 경험

URI
http://hdl.handle.net/10203/296152
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=963365&flag=dissertation
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