1. How to build a Deep Learning network which applies multiple sequence inputs into their corresponding LSTM layers separately, then combines the outputs of LSTM together into a classification layer?

just like this

Answer 1

[Krishna]

Hi,

To build these networks with multiple inputs and multiple outputs you need to understand 3 layers ‘additionLayer’, ‘connectLayers’ and ‘concatenationLayer.’ Please look at these documentation to learn more regarding this,

https://in.mathworks.com/help/deeplearning/ref/nnet.cnn.layer.additionlayer.html

https://in.mathworks.com/help/deeplearning/ref/nnet.cnn.layer.concatenationlayer.html

https://in.mathworks.com/help/deeplearning/ref/nnet.cnn.layergraph.connectlayers.html

For storing data for the training of these kind of networks you need to use datastores. Look at the following documentation to learn more,

https://in.mathworks.com/help/matlab/datastore.html

Also look at the following example to learn how to build multi-input multi-output networks,

https://in.mathworks.com/help/deeplearning/ug/train-network-with-multiple-outputs.html

https://in.mathworks.com/help/deeplearning/ug/multiple-input-and-multiple-output-networks.html

Hope this helps.