TY - JOUR
T1 - Visual Analytics for Explainable Deep Learning
AU - Choo, Jaegul
AU - Liu, Shixia
N1 - Funding Information:
We greatly appreciate the feedback from anonymous reviewers. This work was partially supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. NRF-2016R1C1B2015924) and National NSF of China (No. 61672308). Any opinions, findings, and conclusions or recommendations expressed here are those of the authors and do not necessarily reflect the views of funding agencies.
Publisher Copyright:
© 1981-2012 IEEE.
PY - 2018/7/1
Y1 - 2018/7/1
N2 - Recently, deep learning has been advancing the state of the art in artificial intelligence to a new level, and humans rely on artificial intelligence techniques more than ever. However, even with such unprecedented advancements, the lack of explanation regarding the decisions made by deep learning models and absence of control over their internal processes act as major drawbacks in critical decision-making processes, such as precision medicine and law enforcement. In response, efforts are being made to make deep learning interpretable and controllable by humans. This article reviews visual analytics, information visualization, and machine learning perspectives relevant to this aim, and discusses potential challenges and future research directions.
AB - Recently, deep learning has been advancing the state of the art in artificial intelligence to a new level, and humans rely on artificial intelligence techniques more than ever. However, even with such unprecedented advancements, the lack of explanation regarding the decisions made by deep learning models and absence of control over their internal processes act as major drawbacks in critical decision-making processes, such as precision medicine and law enforcement. In response, efforts are being made to make deep learning interpretable and controllable by humans. This article reviews visual analytics, information visualization, and machine learning perspectives relevant to this aim, and discusses potential challenges and future research directions.
KW - computer graphics
KW - deep learning
KW - explainable deep learning
KW - interactive visualization
UR - http://www.scopus.com/inward/record.url?scp=85049692022&partnerID=8YFLogxK
U2 - 10.1109/MCG.2018.042731661
DO - 10.1109/MCG.2018.042731661
M3 - Article
C2 - 29975192
AN - SCOPUS:85049692022
SN - 0272-1716
VL - 38
SP - 84
EP - 92
JO - IEEE Computer Graphics and Applications
JF - IEEE Computer Graphics and Applications
IS - 4
ER -