What does this fullyconnectedlayer() used for

Ok. I came across this tutorial from mathwork on lstm:

https://www.mathworks.com/help/deeplearning/examples/sequence-to-sequence-regression-using-deep-learning.html

However in the layer options, there is a bit of confusion

what is the fullyconnectedlayer(50) used for?

When I read lstm layers guideline, the fullyconnectedlayer should be the number of response. In the tutorial above, it is a regression problem with 1 response.

https://www.mathworks.com/help/deeplearning/ref/nnet.cnn.layer.lstmlayer.html;jsessionid=bfebe2cd37cf128dc446d1408ee5

This is really confusing. I dont know why there is this fullyconnectedlayer(50) in the tutorial

Answer 1

[Raunak Gupta]

Hi,

The example mentioned in Sequence-to-Sequence Regression Using Deep Learning uses a multi-layer network that is why a fullyConnectedLayer in between is connected. You may also try the example without it but the number of parameters in the Network will decrease which may affect the overall performance (in terms of accuracy) of the Network. The last layer is fullyConnectedLayer(numResponse) which is according the guideline that are mentioned in here.

It’s a general practice in Deep Learning to include fullyConnectedLayer with appropriate outputSize to make the network deep and using dropoutLayer to prevent the network from overfitting.