Folgen
Michael Matena
Michael Matena
PhD Student, UNC Chapel Hill
Keine bestätigte E-Mail-Adresse
Titel
Zitiert von
Zitiert von
Jahr
Exploring the limits of transfer learning with a unified text-to-text transformer
C Raffel, N Shazeer, A Roberts, K Lee, S Narang, M Matena, Y Zhou, W Li, ...
Journal of machine learning research 21 (140), 1-67, 2020
166052020
Merging models with fisher-weighted averaging
MS Matena, CA Raffel
Advances in Neural Information Processing Systems 35, 17703-17716, 2022
1652022
Do transformer modifications transfer across implementations and applications?
S Narang, HW Chung, Y Tay, W Fedus, T Fevry, M Matena, K Malkan, ...
arXiv preprint arXiv:2102.11972, 2021
902021
Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv
C Raffel, N Shazeer, A Roberts, K Lee, S Narang, M Matena, Y Zhou, W Li, ...
arXiv preprint arXiv:1910.10683, 2019
772019
Exploring the limits of transfer learning with a unified text-to-text transformer
A Roberts, C Raffel, K Lee, M Matena, N Shazeer, PJ Liu, S Narang, W Li, ...
Google, Tech. Rep., 2019
462019
T5: Exploring the limits of transfer learning with a unified text-to-text transformer
C Raffel, N Shazeer, A Roberts, K Lee, S Narang, M Matena, Y Zhou, W Li, ...
Journal of Machine Learning Research 21, 1-67, 2020
402020
A combinatorial perspective on the optimization of shallow ReLU networks
MS Matena, CA Raffel
Advances in Neural Information Processing Systems 35, 22187-22198, 2022
12022
NPEFF: Non-Negative Per-Example Fisher Factorization
M Matena, C Raffel
arXiv preprint arXiv:2310.04649, 2023
2023
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–8