Holzinger, Andreas; Plass, Markus (3 de agosto de 2017). «A glass-box interactive machine learning approach for solving NP-hard problems with the human-in-the-loop». arXiv:1708.01104 [cs.AI]
Biecek, Przemyslaw (23 de junho de 2018). «DALEX: explainers for complex predictive models». Journal of Machine Learning Research. 19: 1–5. Bibcode:2018arXiv180608915B. arXiv:1806.08915
Lipton, Zachary C. (10 de junho de 2016). «The Mythos of Model Interpretability». arXiv:1606.03490 [cs.LG]
Doshi-Velez, Finale; Kim, Been (27 de fevereiro de 2017). «Towards A Rigorous Science of Interpretable Machine Learning». arXiv:1702.08608 [stat.ML]
Abdollahi, Behnoush, and Olfa Nasraoui. «Explainable Restricted Boltzmann Machines for Collaborative Filtering.». arXiv:1606.07129 [stat.ML] !CS1 manut: Nomes múltiplos: lista de autores (link)
Holzinger, Andreas; Biemann, Chris (28 de dezembro de 2017). «What do we need to build explainable AI systems for the medical domain?». arXiv:1712.09923 [cs.AI]
Qureshi, M. Atif; Greene, Derek (4 de junho de 2018). «EVE: explainable vector based embedding technique using Wikipedia». Journal of Intelligent Information Systems (em inglês). 53: 137–165. ISSN0925-9902. arXiv:1702.06891. doi:10.1007/s10844-018-0511-x
Aler Tubella, Andrea; Theodorou, Andreas; Dignum, Frank; Dignum, Virginia (2019). Governance by Glass-Box: Implementing Transparent Moral Bounds for AI Behaviour. California: International Joint Conferences on Artificial Intelligence Organization. ISBN978-0-9992411-4-1. doi:10.24963/ijcai.2019/802
Sokol, Kacper; Flach, Peter (2018). «Glass-Box: Explaining AI Decisions With Counterfactual Statements Through Conversation With a Voice-enabled Virtual Assistant». Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. [S.l.: s.n.] pp. 5868–5870. ISBN9780999241127. doi:10.24963/ijcai.2018/865
Tickle, A. B.; Andrews, R.; Golea, M.; Diederich, J. (novembro de 1998). «The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks». IEEE Transactions on Neural Networks. 9: 1057–1068. ISSN1045-9227. PMID18255792. doi:10.1109/72.728352
«"Why Should I Trust You?" | Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining» (em inglês). doi:10.1145/2939672.2939778
Qureshi, M. Atif; Greene, Derek (4 de junho de 2018). «EVE: explainable vector based embedding technique using Wikipedia». Journal of Intelligent Information Systems (em inglês). 53: 137–165. ISSN0925-9902. arXiv:1702.06891. doi:10.1007/s10844-018-0511-x
Biecek, Przemyslaw (23 de junho de 2018). «DALEX: explainers for complex predictive models». Journal of Machine Learning Research. 19: 1–5. Bibcode:2018arXiv180608915B. arXiv:1806.08915
Aivodji, Ulrich; Arai, Hiromi; Fortineau, Olivier; Gambs, Sébastien; Hara, Satoshi; Tapp, Alain (24 de maio de 2019). «Fairwashing: the risk of rationalization». PMLR. International Conference on Machine Learning (em inglês): 161–170
Vidal, Thibaut; Schiffer, Maximilian (2020). «Born-Again Tree Ensembles». PMLR. International Conference on Machine Learning (em inglês). 119: 9743–9753
Tickle, A. B.; Andrews, R.; Golea, M.; Diederich, J. (novembro de 1998). «The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks». IEEE Transactions on Neural Networks. 9: 1057–1068. ISSN1045-9227. PMID18255792. doi:10.1109/72.728352
Edwards, Lilian; Veale, Michael (2017). «Slave to the Algorithm? Why a 'Right to an Explanation' Is Probably Not the Remedy You Are Looking For». Duke Law and Technology Review. 16. 18 páginas. SSRN2972855
Tickle, A. B.; Andrews, R.; Golea, M.; Diederich, J. (novembro de 1998). «The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks». IEEE Transactions on Neural Networks. 9: 1057–1068. ISSN1045-9227. PMID18255792. doi:10.1109/72.728352
Qureshi, M. Atif; Greene, Derek (4 de junho de 2018). «EVE: explainable vector based embedding technique using Wikipedia». Journal of Intelligent Information Systems (em inglês). 53: 137–165. ISSN0925-9902. arXiv:1702.06891. doi:10.1007/s10844-018-0511-x