| Neural message passing for quantum chemistry J Gilmer, SS Schoenholz, PF Riley, O Vinyals, GE Dahl International conference on machine learning, 1263-1272, 2017 | 8354 | 2017 |
| Deep neural networks as gaussian processes J Lee, Y Bahri, R Novak, SS Schoenholz, J Pennington, J Sohl-Dickstein International Conference on Learning Representations, 2017 | 1233 | 2017 |
| Wide neural networks of any depth evolve as linear models under gradient descent J Lee, L Xiao, S Schoenholz, Y Bahri, R Novak, J Sohl-Dickstein, ... Advances in neural information processing systems 32, 2019 | 1060 | 2019 |
| Beyond the imitation game: Quantifying and extrapolating the capabilities of language models A Srivastava, A Rastogi, A Rao, AAM Shoeb, A Abid, A Fisch, AR Brown, ... arXiv preprint arXiv:2206.04615, 2022 | 883 | 2022 |
| 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, 2017 | 688* | 2017 |
| A structural approach to relaxation in glassy liquids SS Schoenholz, ED Cubuk, DM Sussman, E Kaxiras, AJ Liu Nature Physics 12, 469-471, 2016 | 455 | 2016 |
| Identifying structural flow defects in disordered solids using machine-learning methods ED Cubuk, SS Schoenholz, JM Rieser, BD Malone, J Rottler, DJ Durian, ... Physical review letters 114 (10), 108001, 2015 | 443 | 2015 |
| Adversarial spheres J Gilmer, L Metz, F Faghri, SS Schoenholz, M Raghu, M Wattenberg, ... arXiv preprint arXiv:1801.02774, 2018 | 424 | 2018 |
| Deep information propagation SS Schoenholz, J Gilmer, S Ganguli, J Sohl-Dickstein International Conference on Learning Representations, 2016 | 417 | 2016 |
| Dynamical isometry and a mean field theory of cnns: How to train 10,000-layer vanilla convolutional neural networks L Xiao, Y Bahri, J Sohl-Dickstein, S Schoenholz, J Pennington International Conference on Machine Learning, 5393-5402, 2018 | 364 | 2018 |
| Unveiling the predictive power of static structure in glassy systems V Bapst, T Keck, A Grabska-Barwińska, C Donner, ED Cubuk, ... Nature physics 16 (4), 448-454, 2020 | 318 | 2020 |
| Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice J Pennington, S Schoenholz, S Ganguli Advances in neural information processing systems 30, 2017 | 298 | 2017 |
| Structure-property relationships from universal signatures of plasticity in disordered solids ED Cubuk, RJS Ivancic, SS Schoenholz, DJ Strickland, A Basu, ... Science 358 (6366), 1033-1037, 2017 | 285 | 2017 |
| Scaling deep learning for materials discovery A Merchant, S Batzner, SS Schoenholz, M Aykol, G Cheon, ED Cubuk Nature 624 (7990), 80-85, 2023 | 273 | 2023 |
| Statistical mechanics of deep learning Y Bahri, J Kadmon, J Pennington, SS Schoenholz, J Sohl-Dickstein, ... Annual Review of Condensed Matter Physics 11 (1), 501-528, 2020 | 253 | 2020 |
| Neural tangents: Fast and easy infinite neural networks in python R Novak, L Xiao, J Hron, J Lee, AA Alemi, J Sohl-Dickstein, ... International Conference on Learning Representations (Spotlight), 2019 | 251 | 2019 |
| Jax, MD: A framework for differentiable physics S Schoenholz, ED Cubuk Advances in Neural Information Processing Systems (Spotlight) 33, 2020 | 227* | 2020 |
| Mean Field Residual Networks: On the Edge of Chaos G Yang, SS Schoenholz Advances in neural information processing systems, 2017 | 204 | 2017 |
| Finite versus infinite neural networks: an empirical study J Lee, SS Schoenholz, J Pennington, B Adlam, L Xiao, R Novak, ... Advances in neural information processing systems (Spotlight), 2020 | 202 | 2020 |
| A mean field theory of batch normalization G Yang, J Pennington, V Rao, J Sohl-Dickstein, SS Schoenholz International Conference on Learning Representations, 2019 | 196 | 2019 |
Ekin Dogus CubukGoogle DeepMind在 fas.harvard.edu 的电子邮件经过验证
