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)?