Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
slashdave
on Oct 8, 2024
|
parent
|
context
|
favorite
| on:
Differential Transformer
I don't get it. Arbitrary linear combinations are already accommodated via feed forward. What am I missing?
michalsustr
on Oct 8, 2024
|
next
[–]
My hunch is that this effectively creates a differentiable minimax “search” “tree” that can be backpropagated through. Not a tree — a dag really — and not search, but learning. :)
thatsadude
on Oct 9, 2024
|
prev
[–]
True, that's a yellow flag for me.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: