On Interpretability of Artificial Neural Networks: A Survey

Deep learning as performed by artificial deep neural networks (DNNs) has achieved great successes recently in many important areas that deal with text, images, videos, graphs, and so on. However, the black-box nature of DNNs has become one of the primary obstacles for their wide adoption in mission-...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on radiation and plasma medical sciences 2021-11, Vol.5 (6), p.741-760
Main Authors: Fan, Feng-Lei, Xiong, Jinjun, Li, Mengzhou, Wang, Ge
Format: Article
Language:English
Subjects:
Artificial neural networks
Data models
Deep learning
Fuzzy logic
interpretability
Machine learning
Neural networks
survey
Taxonomy
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning as performed by artificial deep neural networks (DNNs) has achieved great successes recently in many important areas that deal with text, images, videos, graphs, and so on. However, the black-box nature of DNNs has become one of the primary obstacles for their wide adoption in mission-critical applications such as medical diagnosis and therapy. Because of the huge potentials of deep learning, the interpretability of DNNs has recently attracted much research attention. In this article, we propose a simple but comprehensive taxonomy for interpretability, systematically review recent studies on interpretability of neural networks, describe applications of interpretability in medicine, and discuss future research directions, such as in relation to fuzzy logic and brain science.
ISSN:2469-7311
2469-7303
DOI:10.1109/TRPMS.2021.3066428