Johannes Rabold, B.Sc.
Teaching Assistant
M. Sc.
Office: WE5/05.045
Office hours: by appointment
Phone: +49-951-863 2865
Email: johannes.rabold(at)uni-bamberg.de
since 10/2017 | Research and Teaching Assistant in the Cognitive Systems Group at Otto-Friedrich-Universität Bamberg, Germany (2021: Winner of the Bavarian Award for Good Teaching ("Preis für Gute Lehre") issued by the state ministry for science and art) |
04/2017- 03/2019 | Applied Computer Science Study at the Faculty of Information Systems and Applied Computer Sciences, Otto-Friedrich-Universität Bamberg, Germany (Master of Science) |
10/2012- 03/2017 | Applied Computer Science Study at the Faculty of Information Systems and Applied Computer Sciences, Otto-Friedrich-Universität Bamberg, Germany (Bachelor of Science) |
Main Research Interests
- Explainable AI
- Deep Learning
- Inductive Logic Programming
- Rabold, J. (2022). A Neural-symbolic Approach for Explanation Generation based on Sub-concept Detection: An Application of Metric Learning for Low-time-budget Labeling. KI - Künstliche Intelligenz. Springer.
- Rabold, J., Siebers, M., & Schmid, U. (2021). Generating Contrastive Explanations for Inductive Logic Programming Based on a Near Miss Approach. Machine Learning. Springer.
- Rabold, J., Schwalbe, G., Schmid, U. (2020). Expressive Explanations of DNNs by Combining Concept Analysis with ILP. 43rd German Conference on Artificial Intelligence.
- Rabold, J., Deininger, H., Siebers, M., & Schmid, U. (2019). Enriching Visual with Verbal Explanations for Relational Concepts – Combining LIME with Aleph. AIMLAI-XKDD (ECML PKDD Workshop).
Schallner, L., Rabold, J., Scholz, O., & Schmid, U. (2019). Effect of Superpixel Aggregation on Explanations in LIME--A Case Study with Biological Data.AIMLAI-XKDD (ECML PKDD Workshop).
Finzel B., Rabold J., Schmid U. (2019) Explaining Relational Concepts: When Visualisation and Visual Interpretation of a Deep Neural Network's Decision are not enough (Abstract). Europäische Konferenz zur Datenanalyse (ECDA, 18.-20. März 2019, Bayreuth), Special Session on Interpretable Machine Learning.
- Rabold, J., Siebers, M., & Schmid, U. (2018, September). Explaining black-box classifiers with ILP – empowering LIME with Aleph to approximate non-linear decisions with relational rules. In International Conference on Inductive Logic Programming (pp. 105-117). Springer, Cham.
Selected Activities
- Elected deputy of the non-professorial teaching staff of the Faculty of Intelligent Systems and Applied Computer Sciences
- Elected member of the student's association of the Faculty of Intelligent Systems and Applied Computer Sciences (during study)
Conference Organization
- Chair for the StudentDay@KI2020
Given Talks (non-conference)
- Invited Talk to RuleML: Enriching Visual with Verbal Explanations for Relational Concepts (2020)
Given Workshops
- Workshop 'Machine Learning and Data Science - Hands-On with KNIME' during the 'Woche der Forschung' (2 times)
- TAO pupil workshop 'Code your own AI'
Participation in Seminars
- Invited participant at the Dagstuhl Seminar on Approaches and Applications of Inductive Programming