Expanding Loss Functions Module #4
LazaroHurtado
started this conversation in
Ideas
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Loss functions depicts the topology of the loss surface which is detrimental to whether or not our model converges to an effective local minimum. To give developers more creative freedom we should expand the loss functions micrograd-rs has to offer. A great place to start is by looking at the functions Pytorch has to offer and implementing those.
Anyone is able to claim which function they will be working on
Beta Was this translation helpful? Give feedback.
All reactions