Abstract
In the summer term 2021, students of computer science have developed and implemented several variants of an Artificial Intelligence that is able to learn string patterns from examples. Every AI is able to answer questions about its behavior, thus, being Explainable AI (XAI). In the summer term 2022, such an XAI is deployed in higher education. Students are encouraged to collaboratively experiment with the XAI. The learning goal is to find out what the XAI is doing and why it is acting in the way observed. There is no need of a human teacher interference. Students learn collaboratively by interacting with the XAI and from chatting with the system about the way it is doing its job. In a sense, the XAI is a domain expert introducing students to its business and disseminating its topical knowledge when being asked to do so. The recent XAI deployment demonstrates the effectiveness of this approach.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Defence Advanced Research Projects Agency (DARPA): Broad agency announcement: Explainable Artificial Intelligence (XAI). DARPA-BAA-16-53. Arlington, VA, USA (2016)
Tjoa, E., Guan, C.: A survey on explainable Artificial Intelligence (XAI): toward medical XAI. Trans. Neural Netw. Learn. Syst. 32, 4793–4813 (2021)
Arieta, A.B., et al.: Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82–115 (2020)
Wilson, R.A., Keil, F.C.: The shadows and shallows of explanation. Mind. Mach. 8, 137–157 (1998)
Keil, F.C.: Explanation and understanding. Annu. Rev. Psychol. 57, 227–254 (2006)
Strube, G.: Wörterbuch der Kognitionswissenschaft. Klett-Cotta, Stuttgart (1996)
Castelvecchi, D.: Can we open the blackbox of AI? Nature 538, 20–23 (2016)
Wahlster, W.: Mehr vom Menschen lernen. Frankfurter Allgemeine Zeitung, 20 September 2020
Lipton, Z.C.: The mythos of model interpretability: in machine learning, the concept of interpretability is both important and slippery. Queue 16, 31–57 (2018)
Lane, H., Howard, C., Hapke, H.M.: Natural Language Processing in Action: Understanding, Analyzing, and Generating Text with Python. Manning Publishing, Shelter Island (2019)
Ortega, A., Fierrez J., Moralez, A., Wang, Z., Ribeiro, T.: Symbolic AI for XAI: evaluating LFIT inductive programming for fair and explainable automatic recruitment. In: 2021 IEEE Winter Conference on Applications of Computer Vision Workshop, Waikola, HI, USA, pp. 78–87 (2021)
Ribeiro, T., Inoue, K.: Learning prime implicant conditions from interpretation transition. In: Davis, J., Ramon, J. (eds.) ILP 2014. LNCS (LNAI), vol. 9046, pp. 108–125. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-23708-4_8
Ribeiro, T., Inoue, K., Sakama, C.: A BDD-based algorithm for learning from interpretation transition. In: Zaverucha, G., Santos Costa, V., Paes, A. (eds.) ILP 2013. LNCS (LNAI), vol. 8812, pp. 47–63. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-44923-3_4
Ribeiro , T.: Studies on learning dynamics of systems from state transitions. Doctoral thesis. The Graduate University of Advanced Studies, School of Multidisciplinary Sciences, Tokyo, Japan (2015)
Inoue, K., Ribeiro, T., Sakama, C.: Learning from interpretation transition. Mach. Learn. 94(1), 51–79 (2014)
Jantke, K.P.: Explainable artificial intelligence (XAI): explainability by design (invited keynote). In: The World Industrial Design Conference WIDC 2021, Yantai, China (2021). https://www.gdio.org/news/173.html
Jantke, K.P., Knauf, R.: Didactic design through storyboarding: standard concepts for standard tools. In: Baltes, B.R., Edwards, L., Galindo, F., et al. (eds.), Proceedings of the 4th International Symposium on Information and Communication Technologies, Cape Town, South Africa, pp. 20–25. Computer Science Press: Trinity College Dublin (2005)
Arnold,O.: Die Therapiesteuerungskomponente einer wissensbasierten Systemarchitektur für Aufgaben der Prozeßführung. DISKI, vol. 130, infix: St. Augustin (1996)
Arnold, O., Jantke, K.P.: Therapy plan generation as program synthesis. In: Arikawa, S., Jantke, K.P. (eds.) AII/ALT -1994. LNCS, vol. 872, pp. 40–55. Springer, Heidelberg (1994). https://doi.org/10.1007/3-540-58520-6_52
Arnold, O., Jantke, K.P.: Planning is learning. In: Dilger, W., Schlosser, M., Zeidler, J., Ittner, A. (eds.), Machine Learning, 1996 Annual Meeting of the Special Interest Group of Machine Learning of the German Computer Science Society (GI), pp. 12-17. TU Chemnitz (1996)
Arnold, O., Jantke, K.P.: AI planning for unique learning experiences: the time travel exploratory games approach. In: Csapó, B., Umohobi, J. (eds.), Proceedings of the 13th International Conference on Computer Supported Education CSEDU 2013, vol. 1, pp. 124–132. SciTePress, Setúbal (2021)
Arnold, O., Franke, R., Jantke, K.P., Wache, H.-H.: Professional training for industrial accident prevention with time travel games. Int. J. Adv. Corp. Learn. 15(1), 20–34 (2022)
Arnold, O., Franke, R., Jantke, K.P., Wache, H.-H.: Dynamic plan generation and digital storyboarding for the professional training of accident prevention with time travel games. In: Guralnick, D., Auer, M.E., Poce, A. (eds.) TLIC 2021. LNNS, vol. 349, pp. 3–18. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-90677-1_1
Arnold, O., Jantke, K.P.: Therapy plans as hierarchically structured graphs. In: Fifth International Workshop on Graph Grammars and Their Application to Computer Science, Williamsburg, VA, USA (1994)
Angluin, D.: Finding patterns common to a set of strings. J. Comput. Syst. Sci. 21, 46–62 (1980)
Nix, R.P.: Editing by example. ACM Trans. Program. Lang. Syst. 7, 600–621 (1985)
Arikawa, S., Kuhara, S., Miyano, S., Mukouchi, Y., Shinohara, A., Shinohara, T.: A machine discovery from amino acid sequences by decision trees over regular patterns. In: Proceedings of the International Conference on Fifth Generation Computer Systems, pp. 618–625 (1992)
Jantke, K.P.: Patterns of game playing behavior as indicators of mastery. In: Ifenthaler, D., Ezeryel, D., Ge, X. (eds.) Assessment in Game-Based Learning: Foundations, Innovations, and Perspectives, pp. 85–103. Springer, Heidelberg (2012). https://doi.org/10.1007/978-1-4614-3546-4_6
Garey, D.S., Johnson, M.: Computers and Intractability: A Guide to the Theory of NP-Completeness. Freeman, London (1979)
Lange, S., Wiehagen, R.: Polynomial-time inference of arbitrary pattern languages. N. Gener. Comput. 8, 361–370 (1991)
Zeugmann, T.: Lange and Wiehagen’s pattern language learning algorithm: an average-case analysis with respect to its total learning time. Ann. Math. Artif. Intell. 23, 117–145 (1998)
Lombrozo, T.: Explanation and abductive inference. In: Holyoak, K.J., Morrison, R.G. (eds.) Oxford Handbook of Thinking and Reasoning, pp. 260–276 (2012)
Acknowledgement
The German Federal Ministry of Labour and Social Affairs has supported this work by an award for the authors’ concept of “Hypothesizing Explainable AI”.
The authors gratefully acknowledge the inspiring and productive exchange of ideas with Leonhard Bollmann, Hannes Dröse, Justin Kraft, Pascal Pflügner, Johannes Veith, Markus Weißflog, and Stefan Woyde. They all contributed to the XAI endeavor within the framework of our Learning Systems module in 2021. They all implemented their own XAI more or less similar to the one demonstrated in the present paper. In this way, they contributed abundant evidence for the possibility to provide Explainable AI to learn with and to learn from.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Arnold, O., Golchert, S., Rennert, M., Jantke, K.P. (2023). Interactive Collaborative Learning with Explainable Artificial Intelligence. In: Auer, M.E., Pachatz, W., Rüütmann, T. (eds) Learning in the Age of Digital and Green Transition. ICL 2022. Lecture Notes in Networks and Systems, vol 633. Springer, Cham. https://doi.org/10.1007/978-3-031-26876-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-26876-2_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26875-5
Online ISBN: 978-3-031-26876-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)