Y
Hacker News
new
|
ask
|
show
|
jobs
The Bayesian Geometry of Transformer Attention
(
arxiv.org
)
4 points
by
samwillis
162 days ago
1 comments
samwillis
162 days ago
Higher level overview and links to the other related papers:
https://medium.com/@vishalmisra/attention-is-bayesian-infere...
link