Peter Hawkins
Peter Hawkins has 2 papers in our library, in 2018–2020; often with Ashish Vaswani, David Belanger, David Dohan.
No OpenAlex profile matched yet.
📄 2 works in our library · 🔗 Cited 540 times in our library · ⭐ Paper Stars ranking: #3143
Fields, topics and concepts
📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksComputer Vision and Pattern Recognition · 2 worksArts and Humanities · 1 workArtificial Intelligence · 1 workLanguage and Linguistics · 1 workComputer Networks and Communications · 1 workHardware and Architecture · 1 work
Works by year
2020s
2010s
Papers
- Rethinking Attention with Performers (2020 · 491 citations)
The standard Transformer scales poorly to long sequences: the attention mechanism requires time and memory that grow quadratically with the number of tokens L. - Mesh-TensorFlow: Deep Learning for Supercomputers (2018 · 203 citations)
Data-parallel training, which splits only the batch across devices, cannot handle models whose parameters exceed a single device's memory.
Co-authors here
- Ashish Vaswani
- David Belanger
- David Dohan
- Dustin Tran
- Krzysztof Choromanski
- Lukasz Kaiser
- Niki Parmar
- Noam Shazeer
- Ryan Sepassi
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/peter-hawkins/