Követés
Andrea Gesmundo
Andrea Gesmundo
Google
E-mail megerősítve itt: google.com - Kezdőlap
Cím
Hivatkozott rá
Hivatkozott rá
Év
Parameter-efficient transfer learning for NLP
N Houlsby, A Giurgiu, S Jastrzebski, B Morrone, Q De Laroussilhe, ...
International conference on machine learning, 2790-2799, 2019
47122019
Temporal coding in spiking neural networks with alpha synaptic function
IM Comsa, K Potempa, L Versari, T Fischbacher, A Gesmundo, ...
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
2782020
Ask the right questions: Active question reformulation with reinforcement learning
C Buck, J Bulian, M Ciaramita, W Gajewski, A Gesmundo, N Houlsby, ...
arXiv preprint arXiv:1705.07830, 2017
1902017
Scaling up models and data with t5x and seqio
A Roberts, HW Chung, G Mishra, A Levskaya, J Bradbury, D Andor, ...
Journal of Machine Learning Research 24 (377), 1-8, 2023
1632023
Transfer Automatic Machine Learning
C Wong, N Houlsby, Y Lu, A Gesmundo
arXiv preprint arXiv:1803.02780, 2018
143*2018
Lemmatisation as a Tagging Task
A Gesmundo, T Samardzic
ACL 2012: the 50th Annual Meeting of the Association for Computational …, 2012
712012
A latent variable model of synchronous syntactic-semantic parsing for multiple languages
A Gesmundo, J Henderson, P Merlo, I Titov
CoNLL 2009: Thirteenth Conference on Computational Natural Language Learning …, 2009
652009
Machine translation of labeled discourse connectives
T Meyer, A Popescu-Belis, N Hajlaoui, A Gesmundo
Proceedings of the 10th Conference of the Association for Machine …, 2012
562012
Evolutionary-neural hybrid agents for architecture search
K Maziarz, M Tan, A Khorlin, M Georgiev, A Gesmundo
arXiv preprint arXiv:1811.09828, 2018
382018
An evolutionary approach to dynamic introduction of tasks in large-scale multitask learning systems
A Gesmundo, J Dean
arXiv preprint arXiv:2205.12755, 2022
302022
Temporal coding in spiking neural networks with alpha synaptic function: learning with backpropagation
IM Comşa, K Potempa, L Versari, T Fischbacher, A Gesmundo, ...
IEEE transactions on neural networks and learning systems 33 (10), 5939-5952, 2021
302021
A continual development methodology for large-scale multitask dynamic ML systems
A Gesmundo
arXiv preprint arXiv:2209.07326, 2022
212022
munet: Evolving pretrained deep neural networks into scalable auto-tuning multitask systems
A Gesmundo, J Dean
arXiv preprint arXiv:2205.10937, 2022
202022
Generating query variants using a trained generative model
J Alakuijala, C Buck, J Bulian, M Ciaramita, W Gajewski, A Gesmundo, ...
US Patent 11,663,201, 2023
182023
Lemmatising Serbian as Category Tagging with Bidirectional Sequence Classification
A Gesmundo, T Samardzic
LREC 2012, 2012
182012
Routing networks with co-training for continual learning
M Collier, E Kokiopoulou, A Gesmundo, J Berent
arXiv preprint arXiv:2009.04381, 2020
172020
Fast task-aware architecture inference
E Kokiopoulou, A Hauth, L Sbaiz, A Gesmundo, G Bartok, J Berent
arXiv preprint arXiv:1902.05781, 2019
152019
Hybrid neural architecture search
A Gesmundo
US Patent 11,544,536, 2023
142023
Gumbel-matrix routing for flexible multi-task learning
K Maziarz, E Kokiopoulou, A Gesmundo, L Sbaiz, G Bartok, J Berent
132019
Composable function-preserving expansions for transformer architectures
A Gesmundo, K Maile
arXiv preprint arXiv:2308.06103, 2023
112023
A rendszer jelenleg nem tudja elvégezni a műveletet. Próbálkozzon újra később.
Cikkek 1–20