I would like to use the Concrete Dropout Framework from GAL in application to recurrent neural networks. There is a great paper about it and the implementation can be found on the website (Thank you so much Yarin!):


He implements a Keras Layer called Concrete Dropout, which can be applied to arbitrairy layers. Nevertheless all his examples are feed forward networks, so here is my question:

Can I use it in a straight forward manner to regularize RNNs?

Example Code in Keras for this would be:


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.