Explaining Trained Neural Networks with Semantic Web Technologies: First Steps

10/11/2017

∙

by   Md Kamruzzaman Sarker, et al.

∙

0

∙

share

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.