Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Feathercrown
6 months ago
|
parent
|
context
|
favorite
| on:
Gradient descent visualization
When I took an ML class we solved that with a temperature parameter, to allow random deviations out of a local minimum. I wonder if there are novel methods now or if they're just improved versions of temperature?
Consider applying for YC's W25 batch! Applications are open till Nov 12.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
