Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
donkeyboy
43 days ago
|
parent
|
context
|
favorite
| on:
The case for the return of fine-tuning
Finetuning is pretty much necessary for regression tasks. Also useful for classification since you can get the direct probabilities in case you want to do some thresholding.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: