Presentation 2017-10-13
[Tutorial Lecture] Understanding Deep Neural Network to Solve the Technical and Social Issues
Takahiro Kubo,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Deep learning leaves many achievements in fields such as images, and the scope of its application is expanding more and more. On the other hand, deep learning has a problem that it is difficult for people to understand what the learned model makes judgments based on what. This point is a problem from the viewpoint of doing business in cooperation with people and also ensuring the safety when executing the task by receiving a complete trust like a highly automated driving car. Therefore, in this presentation, we will introduce the recent studies that tried to clarify the grounds for deep learning decision. In addition, show the examples of its application.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Deep Neural Network / DNN / Visualization / Model Validation
Paper # PRMU2017-92
Date of Issue 2017-10-05 (PRMU)

Conference Information
Committee PRMU
Conference Date 2017/10/12(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Shinichi Sato(NII)
Vice Chair Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron)
Secretary Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST)
Assistant Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Tutorial Lecture] Understanding Deep Neural Network to Solve the Technical and Social Issues
Sub Title (in English)
Keyword(1) Deep Neural Network
Keyword(2) DNN
Keyword(3) Visualization
Keyword(4) Model Validation
1st Author's Name Takahiro Kubo
1st Author's Affiliation TIS(TIS)
Date 2017-10-13
Paper # PRMU2017-92
Volume (vol) vol.117
Number (no) PRMU-238
Page pp.pp.167-168(PRMU),
#Pages 2
Date of Issue 2017-10-05 (PRMU)