Explaining Trained Neural Networks with Semantic Web Technologies: First Steps
Artificial Intelligence
2017-10-13 v1
Abstract
The ever increasing prevalence of publicly available structured data on the World Wide Web enables new applications in a variety of domains. In this paper, we provide a conceptual approach that leverages such data in order to explain the input-output behavior of trained artificial neural networks. We apply existing Semantic Web technologies in order to provide an experimental proof of concept.
Cite
@article{arxiv.1710.04324,
title = {Explaining Trained Neural Networks with Semantic Web Technologies: First Steps},
author = {Md Kamruzzaman Sarker and Ning Xie and Derek Doran and Michael Raymer and Pascal Hitzler},
journal= {arXiv preprint arXiv:1710.04324},
year = {2017}
}