| Universal language model fine-tuning for text classification J Howard, S Ruder ACM: Proceedings of the 56th Annual Meeting of the Association for …, 2018 | 6628 | 2018 |
| An evidence review of face masks against COVID-19 J Howard, A Huang, Z Li, Z Tufekci, V Zdimal, HM van der Westhuizen, ... Proceedings of the National Academy of Sciences 118 (4), e2014564118, 2021 | 1949* | 2021 |
| Fastai: A layered API for deep learning J Howard, S Gugger Information 11 (2), 108, 2020 | 1355 | 2020 |
| Smarter, better, faster, longer: A modern bidirectional encoder for fast, memory efficient, and long context finetuning and inference B Warner, A Chaffin, B Clavié, O Weller, O Hallström, S Taghadouini, ... Proceedings of the 63rd Annual Meeting of the Association for Computational …, 2025 | 512 | 2025 |
| Deep Learning for Coders with fastai and PyTorch J Howard, S Gugger O'Reilly Media, 2020 | 354 | 2020 |
| Imagenette: A smaller subset of 10 easily classified classes from imagenet J Howard GitHub, Mar, 2019 | 231* | 2019 |
| Deep learning-based point-scanning super-resolution imaging L Fang, F Monroe, SW Novak, L Kirk, CR Schiavon, BY Seungyoon, ... Nature Methods 18 (4), 406-416, 2021 | 207 | 2021 |
| Federated benchmarking of medical artificial intelligence with MedPerf A Karargyris, R Umeton, MJ Sheller, A Aristizabal, J George, A Wuest, ... Nature Machine Intelligence 5 (7), 799-810, 2023 | 179 | 2023 |
| MultiFiT: Efficient multi-lingual language model fine-tuning JM Eisenschlos, S Ruder, P Czapla, M Kardas, S Gugger, J Howard EMNLP-IJCNLP: Proceedings of the 2019 Conference on Empirical Methods in …, 2019 | 125 | 2019 |
| Beware default random forest importances T Parr, K Turgutlu, C Csiszar, J Howard March 26, 2018, 2018 | 105* | 2018 |
| De-identification methods for open health data: the case of the Heritage Health Prize claims dataset K El Emam, L Arbuckle, G Koru, B Eze, L Gaudette, E Neri, S Rose, ... Journal of medical Internet research 14 (1), e2001, 2012 | 104 | 2012 |
| The two most important algorithms in predictive modeling today J Howard, M Bowles Strata Conference presentation, February 28, 2012 | 50 | 2012 |
| The matrix calculus you need for deep learning T Parr, J Howard arXiv preprint arXiv:1802.01528, 2018 | 38 | 2018 |
| Big data now: 2012 edition E Dumbill, J Howard, M Zwemer, M Loukides, M Slocum, A Croll, J Steele, ... Sebastopol: O‟ Reilley Media, 2012 | 33 | 2012 |
| The business impact of deep learning J Howard Proceedings of the 19th ACM SIGKDD international conference on Knowledge …, 2013 | 32 | 2013 |
| Designing great data products J Howard, M Zwemer, M Loukides " O'Reilly Media, Inc.", 2012 | 21 | 2012 |
| How to explain gradient boosting T Parr, J Howard Explained. ai, 2018 | 16 | 2018 |
| Applying a Pre-trained Language Model to Spanish Twitter Humor Prediction BFP Czapla, J Howard Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2019). CEUR …, 2019 | 15* | 2019 |
| Decrappification, deoldification, and super resolution J Antic, J Howard, U Manor Facebook f8 conference, 2019 | 11 | 2019 |
| Winning methods for forecasting tourism time series LC Baker, J Howard International Journal of Forecasting 27 (3), 850-852, 2011 | 10 | 2011 |
Sebastian RuderResearch Scientist, MetaVerified email at meta.com
