"Deep Transformers without Shortcuts: Modifying Self-attention for Faithful ..."

Bobby He et al. (2023)

> Home

Details and statistics

DOI: 10.48550/ARXIV.2302.10322

access: open

type: Informal or Other Publication

metadata version: 2023-02-24

- view
  - electronic edition via DOI (open access)
  authority control:
- export record
  dblp key:
  - journals/corr/abs-2302-10322
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2302-10322
Bobby He, James Martens, Guodong Zhang, Aleksandar Botev, Andrew Brock, Samuel L. Smith, Yee Whye Teh:
Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation. CoRR abs/2302.10322 (2023)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.