Explaining Trained Neural Networks with Semantic Web Technologies: First Steps

TitleExplaining Trained Neural Networks with Semantic Web Technologies: First Steps
Publication TypeConference Proceedings
Year of Publication2017
AuthorsKamruzzaman, SMd, Xie, N, Doran, D, Raymer, M, Hitzler, P
Conference NameTwelveth International Workshop on Neural-Symbolic Learning and Reasoning, NeSy
Edition12
Date Published07/2017
Conference LocationLondon, UK
KeywordsArtificial Intelligence
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.

URLhttp://daselab.cs.wright.edu/nesy/NeSy17/

Projects: