I am interested in creating the neural network architecture described in this recent paper. However, I am not sure how to get started. Does TFLearn or Keras allow us to wire the LSTM in such ways? NLU

  • $\begingroup$ As far as i can see from the paper, it is a Transfer learning task. A source domain is mapped to a target domain via natural language. So it is likely, that the LSTM multistack network acts as a grounding facility for reducing the state-space? $\endgroup$ – Manuel Rodriguez Oct 28 '18 at 5:37

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.