| Definitions, methods, and applications in interpretable machine learning WJ Murdoch, C Singh, K Kumbier, R Abbasi-Asl, B Yu Proceedings of the National Academy of Sciences, 2019 | 2671* | 2019 |
| Interpretations are useful: penalizing explanations to align neural networks with prior knowledge L Rieger, C Singh, WJ Murdoch, B Yu International Conference on Machine Learning, 2020 | 295 | 2020 |
| Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs WJ Murdoch, PJ Liu, B Yu International Conference on Learning Representations (oral), 2018 | 289 | 2018 |
| Hierarchical interpretations for neural network predictions C Singh*, WJ Murdoch*, B Yu International Conference on Learning Representations, arXiv preprint arXiv …, 2019 | 199 | 2019 |
| Automatic Rule Extraction from Long Short Term Memory Networks WJ Murdoch, A Szlam International Conference on Learning Representations, 2017 | 140 | 2017 |
| Disentangled attribution curves for interpreting random forests and boosted trees S Devlin, C Singh, WJ Murdoch, B Yu arXiv preprint arXiv:1905.07631, 2019 | 17 | 2019 |
| Extracting structured information from pathology reports using natural language processing and machine learning A Odisho*, B Park, N Altieri, WJ Murdoch, P Carroll, M Coopberberg, B Yu The Journal of Urology 201 (Supplement 4), e1031-e1032, 2019 | 7 | 2019 |
| Expanded alternating optimization of nonconvex functions with applications to matrix factorization and penalized regression WJ Murdoch, M Zhu International conference on computational statistics, 2014 | 4 | 2014 |
| Interpretable deep learning for natural language processing WJ Murdoch UC Berkeley, 2019 | 2 | 2019 |
Bin YUProfessor of Statistics and EECS, UC BerkeleyVerified email at stat.berkeley.edu
