GitLab

algorithms.

if they should be default constructed.

entire std::vector of objects.

the loss isn't being reduced.  Also, there is a stopping condition now based on
how large the current learning rate is.  That is, training stops when the learning
rate gets small enough and it is clear that no progress is being made.

networks.  This revolved mostly around removing really deep template recursions
since that upsets the compiler when you make really deep networks.

method to more efficiently give the input gradient in some instances.

define combination layers made out of other combination layers without being
hassled by the compiler.

in-place.

that contain a different number of samples than their input tensors.

to just regular lists of parameters.

have a tag that refers to the raw input given to a network.