What does explainable AI really mean? A new conceptualization of perspectives D Doran, S Schulz, TR Besold arXiv preprint arXiv:1710.00794, 2017 | 712 | 2017 |
Neural-Symbolic Learning and Reasoning: A Survey and Interpretation TR Besold, AA Garcez, S Bader, H Bowman, P Domingos, P Hitzler, ... Neuro-Symbolic Artificial Intelligence: The State of the Art, 1-51, 2022 | 383* | 2022 |
A historical perspective of explainable Artificial Intelligence R Confalonieri, L Coba, B Wagner, TR Besold Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 11 (1 …, 2021 | 304 | 2021 |
Neural-symbolic learning and reasoning: contributions and challenges AA Garcez, TR Besold, L De Raedt, P Földiak, P Hitzler, T Icard, ... 2015 AAAI Spring Symposium Series, 2015 | 203 | 2015 |
Ultra-strong machine learning: comprehensibility of programs learned with ILP SH Muggleton, U Schmid, C Zeller, A Tamaddoni-Nezhad, T Besold Machine Learning 107, 1119-1140, 2018 | 127 | 2018 |
Using ontologies to enhance human understandability of global post-hoc explanations of black-box models R Confalonieri, T Weyde, TR Besold, FM del Prado Martín Artificial Intelligence 296, 103471, 2021 | 103 | 2021 |
Computational creativity research: towards creative machines TR Besold, M Schorlemmer, A Smaill Atlantis Press, 2015 | 79 | 2015 |
Trepan reloaded: A knowledge-driven approach to explaining black-box models R Confalonieri, T Weyde, TR Besold, F Moscoso del Prado Martín ECAI 2020, 2457-2464, 2020 | 74* | 2020 |
Lessons from infant learning for unsupervised machine learning L Zaadnoordijk, TR Besold, R Cusack Nature Machine Intelligence 4, 510-520, 2022 | 55* | 2022 |
How does predicate invention affect human comprehensibility? U Schmid, C Zeller, T Besold, A Tamaddoni-Nezhad, S Muggleton Inductive Logic Programming: 26th International Conference, ILP 2016, London …, 2017 | 52 | 2017 |
Towards integrated neural–symbolic systems for human-level AI: Two research programs helping to bridge the gaps TR Besold, KU Kühnberger Biologically Inspired Cognitive Architectures 14, 97-110, 2015 | 46 | 2015 |
Can machine intelligence be measured in the same way as human intelligence? T Besold, J Hernández-Orallo, U Schmid KI-Künstliche Intelligenz 29, 291-297, 2015 | 32 | 2015 |
Generalize and blend: Concept blending based on generalization, analogy, and amalgams TR Besold, E Plaza | 31 | 2015 |
Reasoning in non-probabilistic uncertainty: Logic programming and neural-symbolic computing as examples TR Besold, AA Garcez, K Stenning, L van der Torre, M van Lambalgen Minds and Machines 27, 37-77, 2017 | 28 | 2017 |
A match does not make a sense: on the sufficiency of the comparator model for explaining the sense of agency L Zaadnoordijk, TR Besold, S Hunnius Neuroscience of consciousness 2019 (1), niz006, 2019 | 27 | 2019 |
What makes a good explanation? Cognitive dimensions of explaining intelligent machines. R Confalonieri, TR Besold, T Weyde, K Creel, T Lombrozo, ST Mueller, ... CogSci, 25-26, 2019 | 26 | 2019 |
Concept invention R Confalonieri, A Pease, M Schorlemmer, TR Besold, O Kutz, E Maclean, ... Springer, 2018 | 26 | 2018 |
Machine learning security in industry: A quantitative survey K Grosse, L Bieringer, TR Besold, B Biggio, K Krombholz IEEE Transactions on Information Forensics and Security 18, 1749-1762, 2023 | 24* | 2023 |
A narrative in three acts: Using combinations of image schemas to model events TR Besold, MM Hedblom, O Kutz Biologically inspired cognitive architectures 19, 10-20, 2017 | 23 | 2017 |
Towards a domain-independent computational framework for theory blending M Martinez, T Besold, A Abdel-Fattah, KU Kuehnberger, H Gust, ... 2011 AAAI Fall Symposium Series, 2011 | 23 | 2011 |