Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
gdiamos
on March 16, 2025
|
parent
|
context
|
favorite
| on:
Transformers Without Normalization
Sure, but why would one prefer tanh instead of normalization layers if they have the same accuracy?
I suppose normalization kernels have reductions in them, but how hard are reductions in 2025?
Consider applying for YC's Summer 2026 batch! Applications are open till May 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
I suppose normalization kernels have reductions in them, but how hard are reductions in 2025?