Simple Recurrent Units for Highly Parallelizable Recurrence

Tao LeiYu ZhangSida I. WangHui DaiYoav Artzi

   Papers with code   Abstract  PDF

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 scalability... (read more)

Benchmarked Models

No benchmarked models yet. Click here to submit a model.