Lernen von dynamisiertem Feedback in Intelligenten Tutorsystemen
Zusammenfassung der Projektergebnisse
In summary, the project achieved its overarching goals of developing new methods to support learners in learning tasks without formalized domain knowledge. In particular, we developed adaptive dissimilarities to represent solution spaces of learning tasks as well as feedback strategies based on such dissimilarities as well as learner data, extended these strategies to take learners’ behavior over time into account, implemented these techniques in a practical system, and evaluated this system in multiple studies. Beyond these successes, we also provided new ways to visualize learning resources and make the learning process across tasks transparent in resource space models; and we applied transfer learning methods to prosthesis research, thus facilitating the use of advances hand prostheses in patients’ everyday lives. A key to these achievements has been the intense study of solution spaces, both conceptually and practically. We have shown that solution space representations by means of example data and pairwise distances facilitate data analysis, feedback, and ultimately student learning, thus providing a firm basis for future research and future applications in intelligent tutoring systems.
Projektbezogene Publikationen (Auswahl)
- Cluster based feedback provision strategies in intelligent tutoring systems. In Proc. ITS 2012, 2012
Sebastian Gross, Xibin Zhu, Barbara Hammer, and Niels Pinkwart
(Siehe online unter https://doi.org/10.1007/978-3-642-30950-2_127) - Domain-independent proximity measures in intelligent tutoring systems. In Proc. EDM 2013, pages 334–335, 2013
Bassam Mokbel, Sebastian Gross, Benjamin Paaßen, Niels Pinkwart, and Barbara Hammer
- Towards a domainindependent its middleware architecture. In Proc. ICALT 2013. IEEE Computer Society Press, 2013
Sebastian Gross, Bassam Mokbel, Barbara Hammer, and Niels Pinkwart
(Siehe online unter https://doi.org/10.1109/ICALT.2013.124) - Towards providing feedback to students in absence of formalized domain models. In Proc. AIED 2013, 2013
Sebastian Gross, Bassam Mokbel, Barbara Hammer, and Niels Pinkwart
(Siehe online unter https://doi.org/10.1007/978-3-642-39112-5_79) - Example-based feedback provision using structured solution spaces. International Journal of Learning Technology, 9(3):248–280, 2014
Sebastian Gross, Bassam Mokbel, Benjamin Paaßen, Barbara Hammer, and Niels Pinkwart
(Siehe online unter https://doi.org/10.1504/IJLT.2014.065752) - How to select an example? a comparison of selection strategies in example-based learning. In Proc. ITS 2014, 2014
Sebastian Gross, Bassam Mokbel, Barbara Hammer, and Niels Pinkwart
(Siehe online unter https://doi.org/10.1007/978-3-319-07221-0_42) - Learning vector quantization for (dis-)similarities. Neurocomputing, 131:43 – 51, 2014
Barbara Hammer, Daniela Hofmann, Frank-Michael Schleif, and Xibin Zhu
(Siehe online unter https://doi.org/10.1016/j.neucom.2013.05.054) - How do learners behave in help-seeking when given a choice? In Proc. AIED 2015, volume 9112. Springer International Publishing, 2015
Sebastian Gross and Niels Pinkwart
(Siehe online unter https://doi.org/10.1007/978-3-319-19773-9_71) - Metric learning for sequences in relational LVQ. Neurocomputing, 169:306–322, 2015
Bassam Mokbel, Benjamin Paaßen, Frank-Michael Schleif, and Barbara Hammer
(Siehe online unter https://doi.org/10.1016/j.neucom.2014.11.082) - Towards an integrative learning environment for java programming. In Proc. ICALT 2015. IEEE Computer Society Press, 2015
Sebastian Gross and Niels Pinkwart
(Siehe online unter https://doi.org/10.1109/ICALT.2015.75) - Adaptive structure metrics for automated feedback provision in intelligent tutoring systems. Neurocomputing, 192:3–13, 2016
Benjamin Paaßen, Bassam Mokbel, and Barbara Hammer
(Siehe online unter https://doi.org/10.1016/j.neucom.2015.12.108) - Execution traces as a powerful data representation for intelligent tutoring systems for programming. In Proc. EDM 2016, pages 183–190. International Educational Datamining Society, 2016
Benjamin Paaßen, Joris Jensen, and Barbara Hammer
- Orientation and navigation support in resource spaces using hierarchical visualizations. i-com, 16(1), 2017
Sebastian Gross, Marcel Kliemannel, and Niels Pinkwart
(Siehe online unter https://doi.org/10.1515/icom-2016-0043) - Expectation maximization transfer learning and its application for bionic hand prostheses. Neurocomputing, 298:122–133, 2018
Benjamin Paaßen, Alexander Schulz, Janne Hahne, and Barbara Hammer
(Siehe online unter https://doi.org/10.1016/j.neucom.2017.11.072) - The continuous hint factory - providing hints in vast and sparsely populated edit distance spaces. Journal of Educational Datamining, 10(1):1–35, 2018
Benjamin Paaßen, Barbara Hammer, Thomas Price, Tiffany Barnes, Sebastian Gross, and Niels Pinkwart
(Siehe online unter https://doi.org/10.5281/zenodo.3554698) - Tree Edit Distance Learning via Adaptive Symbol Embeddings. In Proc. ICML 2018, pages 3973–3982, 2018
Benjamin Paaßen, Claudio Gallicchio, Alessio Micheli, and Barbara Hammer
- Counteracting electrode shifts in upper-limb prosthesis control via transfer learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 27(5):956–962, 2019
Cosima Prahm, Alexander Schulz, Benjamin Paaßen, Johannes Schoisswohl, Eugenijus Kaniusas, Georg Dorffner, Barbara Hammer, and Oskar Aszmann
(Siehe online unter https://doi.org/10.1109/TNSRE.2019.2907200)
