Explaining Trained Neural Networks with Semantic Web Technologies: First Steps

Authors

Md Kamruzzaman Sarker, Wright State University - Main CampusFollow
Ning Xie, Wright State University - Main CampusFollow
Derek Doran, Wright State University - Main CampusFollow
Michael L. Raymer, Wright State University - Main CampusFollow
Pascal HitzlerFollow

Document Type

Conference Proceeding

Publication Date

7-17-2017

Abstract

The ever increasing prevalence of publicly available struc-tured data on the World Wide Web enables new applications in a varietyof domains. In this paper, we provide a conceptual approach that lever-ages such data in order to explain the input-output behavior of trainedartificial neural networks. We apply existing Semantic Web technologiesin order to provide an experimental proof of concept.

Comments

Proceedings of the Twelfth International Workshop on Neural-Symbolic Learning and Reasoning 2017, London, UK, July 17-18, 2017.

Repository Citation

Sarker, M., Xie, N., Doran, D., Raymer, M. L., & Hitzler, P. (2017). Explaining Trained Neural Networks with Semantic Web Technologies: First Steps. Proceedings of the Twelfth International Workshop on Neural-Symbolic Learning and Reasoning.
https://corescholar.libraries.wright.edu/cse/497