![](https://d3ilqtpdwi981i.cloudfront.net/IKzaAxI6ijhb9LGw2g1UtZSBtps=/425x550/smart/https://bepress-attached-resources.s3.amazonaws.com/uploads/9c/0d/2e/9c0d2eab-b4df-4985-8269-f9a9d851d5d0/thumbnail_c272f5f5-1fc9-45f3-a4bb-c8c2924dfde0.jpg)
Article
Explaining Trained Neural Networks with Semantic Web Technologies: First Steps
Proceedings of the Twelfth International Workshop on Neural-Symbolic Learning and Reasoning
Document Type
Conference Proceeding
Publication Date
7-17-2017
Disciplines
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.
Citation Information
Md Kamruzzaman Sarker, Ning Xie, Derek Doran, Michael L. Raymer, et al.. "Explaining Trained Neural Networks with Semantic Web Technologies: First Steps" Proceedings of the Twelfth International Workshop on Neural-Symbolic Learning and Reasoning (2017) ISSN: 1613-0073 Available at: http://works.bepress.com/derek_doran/54/
Proceedings of the Twelfth International Workshop on Neural-Symbolic Learning and Reasoning 2017, London, UK, July 17-18, 2017.