Every neural network updates its weights through back-propagation.

How is back-propagation used for updating weights in a combination of 2 or more neural networks (e.g.:CNN-LSTM, GAN-CNN, etc.).

For instance a CNN-LSTM model is a CNN model stacked on top of an LSTM model. When CNN model is stacked on top of an LSTM model, do we consider hidden layer of both model or hidden layer of outer model(LSTM)?

  • $\begingroup$ CNN-LSTM is just one continous model so backprop works like usual. GANs-CNN has the same backprop schema as normal GANs. $\endgroup$ – Daniel Nov 12 '18 at 21:48

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.