Fraternal dropout + AWD-LSTM 3-layer (WT2)
Jagiellonian UniversityMila - Quebec AI (originally Montreal Institute for Learning Algorithms)University of Montreal / Université de MontréalLanguage modeling
Developed by Jagiellonian University,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal in 2017, Fraternal dropout + AWD-LSTM 3-layer (WT2) is a language modeling model with 34000000.0 parameters.
About Fraternal dropout + AWD-LSTM 3-layer (WT2)
Recurrent neural networks (RNNs) are important class of architectures among neural networks useful for language modeling and sequential prediction. However, optimizing RNNs is known to be harder compared to feed-forward neural networks. A number of t
Details
- Provider
- Jagiellonian University,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal
- Task
- Language modeling
- Parameters
- 34000000.0
- Released
- 2017-10-31
- Open weights
- No