Re:Computing Higher Order Derivatives of Matrix and Tensor E...
by SoerenL on Friday November 16, 2018 @02:57AM
(#18467268)
Not in its current formulation. It uses a different representation of the tensors. However, a new version/algorithm that will be available in a few months can be used in TF and PyTorch.
[ Parent
| on HN ]
Re:Computing Higher Order Derivatives of Matrix and Tensor E...
by jkam on Friday November 16, 2018 @02:59PM
(#18471523)
Are you referring to the Ricci notation when you are saying it uses a different representation of the tensors?
Do you also plan to add non-differentiable functions like relu?
Re:Computing Higher Order Derivatives of Matrix and Tensor E...
by SoerenL on Sunday November 18, 2018 @02:54PM
(#18482187)
Yeah, I am referring to Ricci notation. TF and PyTorch don't use it. The new version already has relus. This version is targeted at standard formulas (has abs as a non-differentiable function), next version works for deep learning. Never wanted to work on this but there is just no way around it.