Replies: 1 comment
|
Sorry for the late reply! There is no planned work on EBMs. I think you should be able to implement it with a custom training loop, though iirc some optimization methods might require higher order gradients? Currently autodiff is only for first order. |
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
I recently stumbled across a LeCun blog about using Energy Based Models as an alternative to the classical approach.
Is there an initiative to implement the required functionality into BURN?
Cheers Thorsten
All reactions