the parameter 't' in the class 'Drift' on the regression task

Lingkai-Kong / SDE-Net

Code for paper: SDE-Net: Equipping Deep Neural network with Uncertainty Estimates

Apache License 2.0

107 stars 18 forks source link

Closed Pengfight closed 4 years ago

Pengfight commented 4 years ago

Here, the parameter 't' (def forward(self, t, x)) does not seem to be used in practice? why?

Lingkai-Kong commented 4 years ago

We found that adding a time dimension t doesn't affect the performance a lot. It is just our choice of the architecture.

Pengfight commented 4 years ago

get it!