关注
Christoph Molnar
Christoph Molnar
Independent researcher and book author
在 christophmolnar.com 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Interpretable Machine Learning - A Guide for Making Black Box Models Explainable
C Molnar
https://christophm.github.io/interpretable-ml-book/, 2018
6542*2018
Interpretable Machine Learning - A Brief History, State-of-the-Art and Challenges
C Molnar, G Casalicchio, B Bischl
arXiv preprint arXiv:2010.09337, 2020
5582020
iml: An R package for Interpretable Machine Learning
C Molnar, G Casalicchio, B Bischl
Journal of Open Source Software 3, 786, 2018
3742018
Multi-objective counterfactual explanations
S Dandl, C Molnar, M Binder, B Bischl
Bäck T. et al. (eds) Parallel Problem Solving from Nature – PPSN XVI. PPSN …, 2020
2952020
TNF blockers inhibit spinal radiographic progression in ankylosing spondylitis by reducing disease activity: results from the Swiss Clinical Quality Management cohort
C Molnar, A Scherer, X Baraliakos, M de Hooge, R Micheroli, P Exer, ...
Annals of the rheumatic diseases 77 (1), 63-69, 2018
2762018
Explainable AI methods-a brief overview
A Holzinger, A Saranti, C Molnar, P Biecek, W Samek
International workshop on extending explainable AI beyond deep models and …, 2022
2732022
Visualizing the feature importance for black box models
G Casalicchio, C Molnar, B Bischl
Machine Learning and Knowledge Discovery in Databases: European Conference …, 2019
2482019
General pitfalls of model-agnostic interpretation methods for machine learning models
C Molnar, G König, J Herbinger, T Freiesleben, S Dandl, CA Scholbeck, ...
International Workshop on Extending Explainable AI Beyond Deep Models and …, 2020
211*2020
Quantifying Model Complexity via Functional Decomposition for Better Post-Hoc Interpretability
C Molnar, G Casalicchio, B Bischl
Joint European Conference on Machine Learning and Knowledge Discovery in …, 2019
97*2019
Model-agnostic feature importance and effects with dependent features: a conditional subgroup approach
C Molnar, G König, B Bischl, G Casalicchio
Data Mining and Knowledge Discovery, 1-39, 2023
822023
Relative Feature Importance
G König, C Molnar, B Bischl, M Grosse-Wentrup
2020 25th International Conference on Pattern Recognition (ICPR), 9318--9325, 2021
602021
Relating the partial dependence plot and permutation feature importance to the data generating process
C Molnar, T Freiesleben, G König, J Herbinger, T Reisinger, ...
World Conference on Explainable Artificial Intelligence, 456-479, 2023
592023
Estimation of voter transitions based on ecological inference: An empirical assessment of different approaches
A Klima, PW Thurner, C Molnar, T Schlesinger, H Küchenhoff
AStA Advances in Statistical Analysis 100, 133-159, 2016
452016
Sampling, intervention, prediction, aggregation: a generalized framework for model-agnostic interpretations
CA Scholbeck, C Molnar, C Heumann, B Bischl, G Casalicchio
Machine Learning and Knowledge Discovery in Databases: International …, 2020
412020
Errors in palliative care: kinds, causes, and consequences: a pilot survey of experiences and attitudes of palliative care professionals
I Dietz, GD Borasio, C Molnar, C Müller-Busch, A Plog, G Schneider, ...
Journal of palliative medicine 16 (1), 74-81, 2013
362013
Beyond prediction: methods for interpreting complex models of soil variation
AMJC Wadoux, C Molnar
Geoderma 422, 115953, 2022
312022
Scientific inference with interpretable machine learning: Analyzing models to learn about real-world phenomena
T Freiesleben, G König, C Molnar, A Tejero-Cantero
arXiv preprint arXiv:2206.05487, 2022
162022
Marginal effects for non-linear prediction functions
CA Scholbeck, G Casalicchio, C Molnar, B Bischl, C Heumann
Data Mining and Knowledge Discovery, 1-46, 2024
92024
Recursive partitioning by conditional inference
C Molnar
Department of Statistics, University of Munich: Munich, Germany, 2013
92013
Model-agnostic interpretable machine learning
C Molnar
lmu, 2022
52022
系统目前无法执行此操作,请稍后再试。
文章 1–20