how to add a FeedForward layer after my LSTM layer

Réponses (1)

You could add desired layers after your LSTM network layer by specifying them as columns in the layers array.
Consider an example below where fullyConnectedLayer, softmaxLayer and classificationLayer are added after the lstmLayer.
layers = [ ...
sequenceInputLayer(inputSize)
lstmLayer(numHiddenUnits)
fullyConnectedLayer(numClasses)
softmaxLayer
classificationLayer]
Refer here for more information.

2 commentaires

Hi Ajay,
Does fullyConnectedLayer equal to feedforward layer?
I actually just want to know what is a feedforward layer in matlab. All doc that I see is feedforward network. Im searching for feedforward layer.
Could you elaborate on the feedforward layer? What does that layer accomplish?

Connectez-vous pour commenter.

Catégories

En savoir plus sur Deep Learning Toolbox dans Centre d'aide et File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by