Understanding deep networks by visualizing its evidence = 판단 근거 표면화를 통한 딥 네트워크의 이해

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 266
  • Download : 0
Since its advent, deep networks showed amazing performance on various topics in computer vision. The two representative network models are Convolutional Neural Network(CNN), a powerful architecture for treating spatial information in an image, and Long Short-Term Memory(LSTM), which is best known for its exceptional achievements in sequential data. In this paper, we propose for the first time a method to diagnose both CNN and CNN+LSTM network in classification tasks. Our idea is based on analogy between CNN and object processing stages in the human visual cortex. Using analogy from the human visual perception process, we introduce a novel method to figure out a set of critical features for the CNN's classification performance, and call this set of features as evidence. The visualized evidence can explain the reasons when misclassifications occur and helps understand constraints of outperforming networks. Finally, we address the limitations of our work and suggest areas for further study.
Advisors
Kim, Chang Ickresearcher김창익researcher
Description
한국과학기술원 :전기및전자공학부,
Publisher
한국과학기술원
Issue Date
2016
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2016.8 ,[vi, 42 p. :]

Keywords

Deep learning; Visualization; Convolutional Neural Network; Long Short Term Memory; Human Visual Cortex; 딥러닝; 표면화; 네트워크 진단; 근거 표면화; 시각 인지

URI
http://hdl.handle.net/10203/221703
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=663462&flag=dissertation
Appears in Collection
EE-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