On: Keras: Fast Deep Learning Prototyping for Python

[taliesinb]

Any support for hyperparameter selection? That's otherwise a bit of a black art. I skimmed the documentation but didn't see it mentioned.

[_ntka → taliesinb]

Not currently. We are looking to introduce easy interfacing with Spearmint, a library which does bayesian hyperparameter search. This should be part of the v1 release.

[Fede_V → _ntka]

Have you taken a look at this ? https://github.com/HIPS/autograd and paper http://arxiv.org/pdf/1502.03492.pdf

They reverse the computation of the gradient to calculate the derivative wrt the hyper parameters.

[madisonmay → taliesinb]

You also might want to check out Whetlab: https://www.whetlab.com/.