Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
eru
on April 23, 2023
|
parent
|
context
|
favorite
| on:
Will we run out of ML data? Evidence from projecti...
We also used to train neural networks over multiple 'epochs' of the same data.
Can't we keep doing that again?
We had techniques like drop-out and data augmentation to help.
Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
Can't we keep doing that again?
We had techniques like drop-out and data augmentation to help.