| Neural message passing for quantum chemistry J Gilmer, SS Schoenholz, PF Riley, O Vinyals, GE Dahl International Conference on Machine Learning 2017, 1263-1272, 2017 | 1722 | 2017 |
| Relational inductive biases, deep learning, and graph networks PW Battaglia, JB Hamrick, V Bapst, A Sanchez-Gonzalez, V Zambaldi, ... arXiv preprint arXiv:1806.01261, 2018 | 992 | 2018 |
| Sanity checks for saliency maps J Adebayo, J Gilmer, M Muelly, I Goodfellow, M Hardt, B Kim Advances in neural information processing systems 31, 9505-9515, 2018 | 439* | 2018 |
| Adversarial patch TB Brown, D Mané, A Roy, M Abadi, J Gilmer Advances in Neural Information Processing Systems (Workshop Track), 2017 | 384* | 2017 |
| Prediction errors of molecular machine learning models lower than hybrid DFT error FA Faber, L Hutchison, B Huang, J Gilmer, SS Schoenholz, GE Dahl, ... Journal of chemical theory and computation 13 (11), 5255-5264, 2017 | 350* | 2017 |
| Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav) B Kim, M Wattenberg, J Gilmer, C Cai, J Wexler, F Viegas International conference on machine learning, 2668-2677, 2018 | 331 | 2018 |
| Svcca: Singular vector canonical correlation analysis for deep learning dynamics and interpretability M Raghu, J Gilmer, J Yosinski, J Sohl-Dickstein Advances in neural information processing systems, 6076-6085, 2017 | 220 | 2017 |
| Adversarial spheres J Gilmer, L Metz, F Faghri, SS Schoenholz, M Raghu, M Wattenberg, ... arXiv preprint arXiv:1801.02774, 2018 | 203 | 2018 |
| Deep information propagation SS Schoenholz, J Gilmer, S Ganguli, J Sohl-Dickstein International Conference on Learning Representations 2017, 2016 | 186 | 2016 |
| Motivating the rules of the game for adversarial example research J Gilmer, RP Adams, I Goodfellow, D Andersen, GE Dahl arXiv preprint arXiv:1807.06732, 2018 | 122 | 2018 |
| Augmix: A simple data processing method to improve robustness and uncertainty D Hendrycks, N Mu, ED Cubuk, B Zoph, J Gilmer, B Lakshminarayanan arXiv preprint arXiv:1912.02781, 2019 | 103 | 2019 |
| Adversarial examples are a natural consequence of test error in noise N Ford, J Gilmer, N Carlini, D Cubuk arXiv preprint arXiv:1901.10513, 2019 | 77 | 2019 |
| A fourier perspective on model robustness in computer vision D Yin, RG Lopes, J Shlens, ED Cubuk, J Gilmer Advances in Neural Information Processing Systems, 13276-13286, 2019 | 70 | 2019 |
| Improving robustness without sacrificing accuracy with patch gaussian augmentation RG Lopes, D Yin, B Poole, J Gilmer, ED Cubuk arXiv preprint arXiv:1906.02611, 2019 | 41 | 2019 |
| Adversarial examples are a natural consequence of test error in noise J Gilmer, N Ford, N Carlini, E Cubuk International Conference on Machine Learning, 2280-2289, 2019 | 32 | 2019 |
| Input switched affine networks: An RNN architecture designed for interpretability JN Foerster, J Gilmer, J Chorowski, J Sohl-Dickstein, D Sussillo International Conference on Machine Learning 2017, 1136-1145, 2016 | 32* | 2016 |
| Mnist-c: A robustness benchmark for computer vision N Mu, J Gilmer arXiv preprint arXiv:1906.02337, 2019 | 31 | 2019 |
| Composition limits and separating examples for some Boolean function complexity measures J Gilmer, M Saks, S Srinivasan Combinatorica 36 (3), 265-311, 2016 | 24 | 2016 |
| A new approach to the sensitivity conjecture J Gilmer, M Koucký, ME Saks Proceedings of the 2015 Conference on Innovations in Theoretical Computer …, 2015 | 23* | 2015 |
| A local central limit theorem for triangles in a random graph J Gilmer, S Kopparty Random Structures & Algorithms 48 (4), 732-750, 2016 | 18 | 2016 |
Samuel S. SchoenholzGoogle BrainVerified email at google.com
