Deep learning layer with custom backward() function
- In order to evaluate this custom layer, do I need to encapsulate this layer in a dlgraph/dlnetwork (a 2-layer network, since it also needs an input layer) so that I can then calling .predict() on this network ? Is there anything simpler, without having to build a network ? It would be nice if one could call something like the following, and the underlying gradient trace would be built to go through my custom backward function: y = myLayer.predict(x);
- I am using the automatic differentiation for second-order derivatives available in the R2021a prelease. Does this support layers with custom backward() function ?