Hybrid AI: Combined use of knowledge and data

Further sources and further reading:

• Androsch, H., Knoll, W., Plimon, A. (Eds.) (2022): KI in der Praxis, Applying AI.
  Online: https://www.ait.ac.at/fileadmin/cmc/downloads/News/efatec22/TG2022-Book-165x240-SCR.pdf
• Beyerer, J. & Müller-Quade, J. et al. (2022): KI-Systeme schützen, Missbrauch verhindern – Maßnahmen und Szenarien in fünf Anwendungsgebieten. Whitepaper aus der Plattform Lernende Systeme, München. https://doi.org/10.48669/pls_2022-2
• De Raedt, L. et al. (2020): From Statistical Relational to Neuro-Symbolic Artificial Intelligence.
  Online: https://arxiv.org/pdf/2003.08316.pdf
• Folgheraiter, M. et al. (2012): Measuring the Improvement of the Interaction Comfort of a Wearable Exoskeleton. In International Journal of Social Robotics, Springer Netherlands, volume 4, number 3, pages 285-302.
• Gartner (2022): What’s New in Artificial Intelligence from the 2022 Gartner Hype Cycle. Online: https://www.gartner.com/en/articles/what-s-new-in-artificial-intelligence-from-the-2022-gartner-hype-cycle
• Goodfelllow, I., Bengio, Y., Courville, A. (2016): Deep Learning. The MIT Press. Cambridge, Massachusetts.
• Görz, G., Schmid, U., Braun, T. (2021): Handbuch der Künstlichen Intelligenz (Aufl. 6). De Gruyter. Berlin, Bosten. https://doi.org/10.1515/9783110659948
• Grundt, D. et al. (2022): Projekt KI Wissen. Conjoint Whitepaper Deliverable D1 & D4. Online: https://www.kiwissen.de/fileadmin/KI_Wissen/Downloads/KI-WI_D1_D4_Conjoint.pdf
• Hamilton, K., Nayak, A., Božic, B., Luca, L. (2022): Is Neuro-Symbolic AI Meeting its Promise in Natural
  Language Processing? A Structured Review. https://doi.org/10.48550/arXiv.2202.12205
• Hitzler, P., Eberhart, A., Ebrahimi, M., Saker, K. & Zhou, L. (06 2022): Neuro-symbolic approaches in artificial intelligence. National Science Review, 9(6). Online: https://academic.oup.com/nsr/article/9/6/nwac035/6542460
• Ilkou, E. & Koutraki, M. (2020): Symbolic Vs Sub-symbolic AI Methods: Friends or Enemies? CIKM. Online: http://ceur-ws.org/Vol-2699/paper06.pdf
• Kautz, H. (8/29/2021): The third AI summer: AAAI Robert S. Engelmore Memorial. AI Magazin, 43. Online: https://henrykautz.com/papers/AI%20Magazine%20-%202022%20-%20Kautz%20-%20The%20third%20AI%20summer%20%20AAAI%20Robert%20S%20%20Engelmore%20Memorial%20Lecture.pdf
• Kersting, K. (4/17/2022): Put up or shut up – The French Hybrid AI system NooK beats world champions at Bridge. Online: https://ml-research.github.io/papers/kersting2022welt_putUp.pdf
• Kirchner, E. et al. (2013): Towards Assistive Robotics for Home Rehabilitation. In Proceedings of the 6th International Conference on Biomedical Electronics and Devices, (BIODEVICE -13), 11.2. – 14.2.2013, Barcelona, o. A., Feb/2013.
• Kirchner, E. A., Fairclough, S. H. & Kirchner, F. (2019): Embedded Multimodal Interfaces in Robotics: Applications, Future Trends, and Societal Implications. https://doi.org/10.26092/elib/2316
• Kokel, H. (2020): Types of Neuro-Symbolic Systems. Online: https://harshakokel.com/posts/neurosymbolic-systems/#references
• LAMARR Institute (2023): Hybrides maschinelles lernen. Online: https://lamarr-institute.org/de/forschung/
• Löser, A., Tresp, V. et al. (2023): Große Sprachmodelle – Grundlagen, Potenziale und Herausforderungen für die Forschung. Whitepaper aus der Plattform Lernende Systeme, München. https://doi.org/10.48669/pls_2023-3
• Manhaeve, R. et al. (2018): DeepProbLog: Neural Probabilistic Logic Programming. https://doi.org/10.48550/arXiv.1805.10872
• Marcus, G. (2022): Hybrid AI: A new way to make machine minds that really think like us. Online: https://www.newscientist.com/article/mg25333740-900-hybrid-ai-a-new-way-to-make-machine-minds-that-really-think-like-us/
• Marcus, G. (2022): Deep Learning Is Hitting a Wall. Online: https://nautil.us/deep-learning-is-hitting-a-wall-238440/
• Müller, F., Schüssler, M., Kirchner, E. A. (2021): Ein „KI-TÜV“ für Europa? Eckpunkte einer horizontalen Regulierung Algorithmischer Entscheidungssysteme. In 6. Tagung GRUR Junge Wissenschaft, 4.6. – 5.6.2021, Virtual, Nomos, pages 85-106, Jun/2021.
• Patel, D. & Ott, E. (2022): Using Machine Learning to Anticipate Tipping Points and Extrapolate to Post-Tipping Dynamics of Non-Stationary Dynamical Systems. Online: https://arxiv.org/pdf/2207.00521.pdf
• Rabold, J., Schwalbe, G. & Schmid, U. (2020): Expressive explanations of DNNs by combining concept analysis with ILP. In KI 2020: Advances in Artificial Intelligence: 43rd German Conference on AI (pp. 148-162). Springer.
• Saker, K. et al. (2021): Neuro-Symbolic Artificial Intelligence. Current Trends. Online: https://arxiv.org/pdf/2105.05330.pdf
• Schmid, U. & Finzel, B. (2020): Mutual explanations for cooperative decision making in medicine. KI-Künstliche Intelligenz, 34(2), 227-233. https://doi.org/10.1007/s13218-020-00633-2
• Schmid, U. (2022): Hybrid, Explanatory, Interactive Machine Learning – Towards Trustworthy Human-AI Partnerships. Online: https://aic20.aass.oru.se/speaker-details.html#schmid
• Teso, S. & Kersting, K. (2018): Explanatory Interactive Machine Learning. https://doi.org/10.1145/3306618.3314293
• van Bekkum, M., de Boer, M., van Harmelen, F. & Meyer-Vitali, A. (2021): Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases. Online: https://arxiv.org/pdf/2102.11965.pdf
• Wolfram, S. (2023): Wolfram|Alpha as the Way to Bring Computational Knowledge Superpowers to ChatGPT. Online: https://writings.stephenwolfram.com/2023/01/wolframalpha-as-the-way-to-bring-computational-knowledgesuperpowers-to-chatgpt/