Abstract
AbstractIn this paper, we present a modular methodology that combines state-of-the-art methods in (stochastic) machine learning with well-established methods in inductive logic programming (ILP) and rule induction to provide efficient and scalable algorithms for the classification of vast data sets. By construction, these classifications are based on the synthesis of simple rules, thus providing direct explanations of the obtained classifications. Apart from evaluating our approach on the common large scale data sets MNIST, Fashion-MNIST and IMDB, we present novel results on explainable classifications of dental bills. The latter case study stems from an industrial collaboration with Allianz Private Krankenversicherung which is an insurance company offering diverse services in Germany.
Funder
University of Innsbruck and Medical University of Innsbruck
Publisher
Springer Science and Business Media LLC
Reference56 articles.
1. An, S., Lee, M.J., Park, S., Yang, H., So, J. (2020) An ensemble of simple convolutional neural network models for MNIST digit recognition. CoRR
2. Asadi, S., & Shahrabi, J. (2016). RipMC: RIPPER for multiclass classification. Neurocomputing, 191, 19–33. https://doi.org/10.1016/j.neucom.2016.01.010
3. Brunk, C., Pazzani, M.J.: An investigation of noise-tolerant relational concept learning algorithms. In: Proceedings of the Eighth International Workshop (ML91), pp. 389–393 (1991). https://doi.org/10.1016/b978-1-55860-200-7.50080-5
4. Burkart, N., & Huber, M. F. (2021). A survey on the explainability of supervised machine learning. Journal of Artificial Intelligence Research https://doi.org/10.1613/jair.1.12228
5. Burkhardt, S., Brugger, J., Wagner, N., Ahmadi, Z., Kersting, K., Kramer, S.: Rule extraction from binary neural networks with convolutional rules for model validation. Frontiers in Artificial Intelligence 4 (2021). https://doi.org/10.3389/frai.2021.642263