Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey

Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized as being non-transparent and their predictions not traceable by humans. Furthermore, the models le...

Full description

Saved in:
Bibliographic Details
Published inMachine learning and knowledge extraction Vol. 3; no. 4; pp. 966 - 989
Main Authors Buhrmester, Vanessa, Münch, David, Arens, Michael
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.12.2021
Subjects
Algorithms
Artificial intelligence
Artificial neural networks
Automation
Bias
Boxes
Classification
Computer vision
Credit scoring
Decision making
Deep learning
ethics
explainable AI
explainer
explanator
General Data Protection Regulation
interpretability
Machine learning
Mathematical models
Multilayers
Neural networks
Taxonomy
trust
Online AccessGet full text

Cover

More Information
Summary:Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized as being non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificially generated datasets, which often do not reflect reality. By basing decision-making algorithms on Deep Neural Networks, prejudice and unfairness may be promoted unknowingly due to a lack of transparency. Hence, several so-called explanators, or explainers, have been developed. Explainers try to give insight into the inner structure of machine learning black boxes by analyzing the connection between the input and output. In this survey, we present the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about the taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.
ISSN:2504-4990
2504-4990
DOI:10.3390/make3040048