Transformer + Simple Recurrent Unit
ASAPPCornell UniversityGooglePrinceton UniversityTranslation
Transformer + Simple Recurrent Unit is translation model published by ASAPP,Cornell University,Google,Princeton University in 2018 featuring 90000000.0 parameters.
About Transformer + Simple Recurrent Unit
Common recurrent neural architectures scale poorly due to the intrinsic difficulty in parallelizing their state computations. In this work, we propose the Simple Recurrent Unit (SRU), a light recurrent unit that balances model capacity and scalabilit
Details
- Provider
- ASAPP,Cornell University,Google,Princeton University
- Task
- Translation
- Parameters
- 90000000.0
- Released
- 2018-09-17
- Open weights
- No