| Explaining individual predictions when features are dependent: More accurate approximations to Shapley values K Aas, M Jullum, A Løland Artificial Intelligence, 2019 | 593 | 2019 |
| Detecting money laundering transactions with machine learning M Jullum, A Løland, RB Huseby, G Ånonsen, J Lorentzen Journal of Money Laundering Control 23 (1), 173-186, 2020 | 154 | 2020 |
| A Gaussian-based framework for local Bayesian inversion of geophysical data to rock properties M Jullum, O Kolbjørnsen Geophysics 81 (3), R75-R87, 2016 | 54 | 2016 |
| Parametric or nonparametric: The FIC approach M Jullum, NL Hjort Statistica Sinica, 951-981, 2017 | 34 | 2017 |
| shapr: An R-package for explaining machine learning models with dependence-aware Shapley values N Sellereite, M Jullum Journal of Open Source Software, 2020 | 23 | 2020 |
| What price semiparametric Cox regression? M Jullum, NL Hjort Lifetime data analysis 25 (3), 406-438, 2019 | 23 | 2019 |
| Bayesian AVO inversion to rock properties using a local neighborhood in a spatial prior model O Kolbj⊘ rnsen, A Buland, R Hauge, P R⊘ e, M Jullum, RW Metcalfe, ... The Leading Edge 35 (5), 431-436, 2016 | 23 | 2016 |
| Explaining predictive models with mixed features using Shapley values and conditional inference trees A Redelmeier, M Jullum, K Aas Machine Learning and Knowledge Extraction: 4th IFIP TC 5, TC 12, WG 8.4, WG …, 2020 | 22 | 2020 |
| Explaining predictive models using Shapley values and non-parametric vine copulas K Aas, T Nagler, M Jullum, A Løland Dependence modeling 9 (1), 62-81, 2021 | 20 | 2021 |
| Using Shapley values and variational autoencoders to explain predictive models with dependent mixed features LHB Olsen, IK Glad, M Jullum, K Aas Journal of machine learning research 23 (213), 1-51, 2022 | 19 | 2022 |
| Comparison of contextual importance and utility with lime and Shapley values K Främling, M Westberg, M Jullum, M Madhikermi, A Malhi International Workshop on Explainable, Transparent Autonomous Agents and …, 2021 | 18 | 2021 |
| groupShapley: Efficient prediction explanation with Shapley values for feature groups M Jullum, A Redelmeier, K Aas arXiv preprint arXiv:2106.12228, 2021 | 12 | 2021 |
| Pairwise local Fisher and naive Bayes: Improving two standard discriminants H Otneim, M Jullum, D Tjøstheim Journal of econometrics 216 (1), 284-304, 2020 | 7 | 2020 |
| A comparative study of methods for estimating conditional Shapley values and when to use them LHB Olsen, IK Glad, M Jullum, K Aas arXiv preprint arXiv:2305.09536, 2023 | 6 | 2023 |
| MCCE: Monte Carlo sampling of realistic counterfactual explanations A Redelmeier, M Jullum, K Aas, A Løland arXiv preprint arXiv:2111.09790, 2021 | 6 | 2021 |
| Efficient and simple prediction explanations with groupShapley: A practical perspective M Jullum, A Redelmeier, K Aas 2nd Italian Workshop on Explainable Artificial Intelligence 3014, 28-43, 2021 | 6 | 2021 |
| Estimating seal pup production in the Greenland Sea by using Bayesian hierarchical modelling M Jullum, T Thorarinsdottir, FE Bachl Journal of the Royal Statistical Society: Series C (Applied Statistics) 69 …, 2020 | 4 | 2020 |
| Investigating mesh‐based approximation methods for the normalization constant in the log Gaussian Cox process likelihood M Jullum Stat 9 (1), e285, 2020 | 4 | 2020 |
| Parametric or nonparametric: the FIC approach for stationary time series GH Hermansen, NL Hjort, M Jullum Proceedings of the 60th World Statistics Congress of the International …, 2015 | 3 | 2015 |
| Explaining individual predictions when features are dependent: More accurate approximations to Shapley values (2020) K Aas, M Jullum, A Løland URL: http://arxiv. org/abs, 1903 | 3 | 1903 |
Kjersti AasAssistant research director Norsk Regnesentral在 nr.no 的电子邮件经过验证
