Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
dataangel
on Jan 23, 2022
|
parent
|
context
|
favorite
| on:
Fast and Accurate Sparse Networks (2021)
If you train the model before you deploy it, why can’t you densely pack the nonzero weights? This is what any SparseMatrix class would do for you.
Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
