Filter löschen
Filter löschen

train deep network with lstm layer with missing (NaN) data input and target (not synced)

1 Ansicht (letzte 30 Tage)
is it possible to train a lstm network with NaN values on input and target data like we can with timedelay nets (in this case there exists the fixunknowns function?
I tried a simple case adding just 1 NaN value and the training didn't converged....
Is there a "fixunknown function" for deep networks...

Antworten (0)




Community Treasure Hunt

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

Start Hunting!

Translated by