| Explaining deep neural networks and beyond: A review of methods and applications W Samek, G Montavon, S Lapuschkin, CJ Anders, KR Müller Proceedings of the IEEE 109 (3), 247-278, 2021 | 1065 | 2021 |
| Explanations can be manipulated and geometry is to blame AK Dombrowski, M Alber, C Anders, M Ackermann, KR Müller, P Kessel Advances in neural information processing systems 32, 2019 | 370 | 2019 |
| Finding and removing clever hans: Using explanation methods to debug and improve deep models CJ Anders, L Weber, D Neumann, W Samek, KR Müller, S Lapuschkin Information Fusion 77, 261-295, 2022 | 122 | 2022 |
| Toward interpretable machine learning: Transparent deep neural networks and beyond W Samek, G Montavon, S Lapuschkin, CJ Anders, KR Müller arXiv preprint arXiv:2003.07631 2, 2020 | 114 | 2020 |
| Estimation of thermodynamic observables in lattice field theories with deep generative models KA Nicoli, CJ Anders, L Funcke, T Hartung, K Jansen, P Kessel, ... Physical review letters 126 (3), 032001, 2021 | 105 | 2021 |
| Fairwashing explanations with off-manifold detergent CJ Anders, P Pasliev, AK Dombrowski, KR Müller, P Kessel Thirty-seventh International Conference on Machine Learning, 2020 | 101 | 2020 |
| Towards robust explanations for deep neural networks AK Dombrowski, CJ Anders, KR Müller, P Kessel Pattern Recognition 121, 108194, 2022 | 71 | 2022 |
| Software for dataset-wide XAI: from local explanations to global insights with Zennit, CoRelAy, and ViRelAy CJ Anders, D Neumann, W Samek, KR Müller, S Lapuschkin arXiv preprint arXiv:2106.13200, 2021 | 71 | 2021 |
| Understanding patch-based learning of video data by explaining predictions CJ Anders, G Montavon, W Samek, KR Müller Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, 297-309, 2019 | 31* | 2019 |
| Detecting and mitigating mode-collapse for flow-based sampling of lattice field theories KA Nicoli, CJ Anders, T Hartung, K Jansen, P Kessel, S Nakajima Physical Review D 108 (11), 114501, 2023 | 15 | 2023 |
| Analyzing imagenet with spectral relevance analysis: Towards imagenet un-hans’ ed CJ Anders, T Marinc, D Neumann, W Samek, KR Müller, S Lapuschkin arXiv preprint arXiv:1912.11425 2 (3), 2019 | 13 | 2019 |
| Machine learning of thermodynamic observables in the presence of mode collapse KA Nicoli, C Anders, L Funcke, T Hartung, K Jansen, P Kessel, ... arXiv preprint arXiv:2111.11303, 2021 | 9 | 2021 |
| PatClArC: Using pattern concept activation vectors for noise-robust model debugging F Pahde, L Weber, CJ Anders, W Samek, S Lapuschkin arXiv preprint arXiv:2202.03482, 2022 | 8 | 2022 |
| Toward interpretable machine learning: Transparent deep neural networks and beyond. arXiv 2020 W Samek, G Montavon, S Lapuschkin, CJ Anders, KR Müller arXiv preprint arXiv:2003.07631, 2020 | 8 | 2020 |
| Toward interpretable machine learning: Transparent deep neural networks and beyond. arXiv W Samek, G Montavon, S Lapuschkin, CJ Anders, KR Müller arXiv preprint arXiv:2003.07631, 2020 | 8 | 2020 |
| Physics-informed bayesian optimization of variational quantum circuits K Nicoli, CJ Anders, L Funcke, T Hartung, K Jansen, S Kühn, KR Müller, ... Advances in Neural Information Processing Systems 36, 2024 | 7 | 2024 |
| XAI for analyzing and unlearning spurious correlations in ImageNet CJ Anders, D Neumann, T Marinc, W Samek, KR Müller, S Lapuschkin Proceedings of the 2020 ICML Workshop on Extending Explainable AI Beyond …, 2020 | 6 | 2020 |
| From hope to safety: Unlearning biases of deep models via gradient penalization in latent space M Dreyer, F Pahde, CJ Anders, W Samek, S Lapuschkin Proceedings of the AAAI Conference on Artificial Intelligence 38 (19), 21046 …, 2024 | 5 | 2024 |
| Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence F Pahde, M Dreyer, L Weber, M Weckbecker, CJ Anders, T Wiegand, ... arXiv preprint arXiv:2202.03482, 2022 | 3 | 2022 |
| From Hope to Safety: Unlearning Biases of Deep Models by Enforcing the Right Reasons in Latent Space M Dreyer, F Pahde, CJ Anders, W Samek, S Lapuschkin arXiv preprint arXiv:2308.09437, 2023 | 2 | 2023 |
Klaus-Robert MüllerGoogle DeepMind & TU Berlin & Korea University & Max Planck Institute for Informatics, GermanyVerified email at tu-berlin.de
