Topics

Hybrid Learning and Reasoning

Seminar an der Universität des Saarlandes, Fachrichtung Informatik, LSF 123624

The topics for seminar time slots (see schedule) are as follows. Currently assigned topics are marked in red.

Selected background literature is indicated below; topic reference papers are available in the web or on request from seminar organizers.

Topic#	Topic
1	Learning with symbolic semantic prior H. Zhang et al. (2019): Faster and Safer Training by Embedding High-Level Knowledge into Deep Reinforcement Learning. arXiv preprint arXiv:1910.09986.
2	Learning with derived semantic prior N. Bougie, L.K. Cheng, R. Ichise (2018): Combining Deep Reinforcement Learning with Prior Knowledge and Reasoning. ACM Applied Computing Review, 18(2):33-45
3	Learning intermediate symbolic abstraction for learning R. Toro Icarte, TQ. Klassen, R. Valenzano & SA. McIlraith (2018): Teaching Multiple Tasks to an RL Agent using LTL. Proceedings of 17th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS).
4	Learning intermediate symbolic abstraction for reasoning F. Pusse & M. Klusch (2019): Hybrid Online POMDP Planning and Deep Reinforcement Learning for Safer Self-Driving Cars. Proceedings of IEEE Intelligent Vehicles Symposium (IV).
5	Meta-reasoning for control D. Lyu, F. Yang, B. Liu & S. Gustafson (2019): SDRL: Interpretable and Data-Efficient Deep Reinforcement Learning Leveraging Symbolic Planning. Proceedings of AAAI Conference on Artificial Intelligence (AAAI).
6	Meta-reasoning for learning to reason T. Rocktäschel & S. Riedel (2017): End-to-end Differentiable Proving. Proceedings of Advances in Neural Information Processing Systems (NIPS).

Selected background references:

F. van Harmelen, A.T. Teije (2019). A Boxology of Design Patterns for Hybrid Learning and Reasoning Systems.Journal of Web Engineering, 18(1-3):97-124, Rivers; also at https://arxiv.org/pdf/1905.12389
A.D. Garcez et al. (2019). Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning. arXiv preprint arXiv:1905.06088. https://arxiv.org/pdf/1905.06088
Tarek R. Besold et al. /2017): Neural-Symbolic Learning and Reasoning: A Survey and Interpretation.
https://arxiv.org/pdf/1711.03902
P. Hitzler, F. Bianchi, M. Ebrahimi & M.K. Sarker (2019): Neural-Symbolic Integration and the Semantic Web. http://www.semantic-web-journal.net/system/files/swj2188.pdf
International Workshop Series on Neural-Symbolic Learning and Reasoning (since 2005) and other related material: http://www.neural-symbolic.org/
International Workshop Series on Semantic Deep Learning (2017a, 2017b, 2018, 2019)
Deep Learning:

I.J. Goodfellow, Y. Bengio, A. Courville (2016): Deep Learning. MIT Press,
M. Nielsen (2017): Neural Networks and Deep Learning. http://neuralnetworksanddeeplearning.com/index.html
L. Deng (2014): A Tutorial Survey of Architectures, Algorithms, and Applications for Deep Learning. APSIPA Transactions on Signal and Information Processing, 3, e2.
http://deeplearning.net

P. Hitzler, M. Kroetzsch, S. Rudolph (2009): Foundations of Semantic Web Technologies. Chapman & Hall/CRC. http://www.semantic-web-book.org/page/Foundations_of_Semantic_Web_Technologies
A. Dengel (Hrsg.) (2012): Semantische Technologien - Grundlagen, Konzepte, Anwendungen. Springer