I am working on a text based autoencoder, and was happy to see I can feed a variable length text sequence into my network and use SequenceLastLayer[] after a GatedRecurrentLayer[] to only get the final output vector. However, is there a function in the neural network framework that allows me to take a fixed length vector and, using a GatedRecurrentLayer[], create a variable length text sequence until a stop character is reached? Thanks!

  • $\begingroup$ One thought I had is just to have a maximal length output sequence that the network can handle, and I could generate a stop character so that, at some point in the output, I would know where the intended output stops, but I'm not sure how this could be trained as efficiently in this way. $\endgroup$ – Jmeeks29ig Apr 14 '19 at 19:43

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.