Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
dartos
on Dec 24, 2023
|
parent
|
context
|
favorite
| on:
"Attention", "Transformers", in Neural Network "La...
Can you link some of those papers?
sischoel
on Dec 25, 2023
[–]
I am not sure if this was the very first paper talking about attention, but
https://arxiv.org/abs/1409.0473
from 2014 is a famous one.
What is still missing there, is the idea of self-attention.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
