Within this project, the Data Semantics Laboratory focuses on the development of methods to explain the behavior of deep learning systems.
Our first experiments concerning the use of DL-Learner to explain trained artificial neural networks.
Ohio Federal Research Network
M. K. Sarker and Hitzler, P., “Efficient Concept Induction for Description Logics”, in AAAI Conference on Artificial Intelligence, Honolulu, US, 2019, vol. 33. Efficient Concept Induction for Description Logics.pdf (288.86 KB)
M. K. Sarker, Xie, N., Doran, D., Raymer, M., and Hitzler, P., “Explaining Trained Neural Networks with Semantic Web Technologies: First Steps”, Twelveth International Workshop on Neural-Symbolic Learning and Reasoning, NeSy. London, UK, 2017. 2017-nesy-xai.pdf (2.09 MB)
M. Labaf, “ Propositional rule extraction from neural networks under background knowledge”, in Twelfth International Workshop on Neural-Symbolic Learning and Reasoning, 2017. main.pdf (270.11 KB)
N. Xie, Sarker, M. K., Doran, D., Hitzler, P., and Raymer, M., “Relating Input Concepts to Convolutional Neural Network Decisions”, NIPS 2017 Workshop: Interpreting, Explaining and Visualizing Deep Learning, NIPS IEVDL 2017. NIPS, CA, USA, 2017. Relating Input Concepts to Convolutional Neural Network Decisions.pdf (2.35 MB)