Fix problem with NarX network

1 visualizzazione (ultimi 30 giorni)
FRANCISCO
FRANCISCO il 20 Mar 2013
Very good, could rise as a snapshot or to explain the problem presented to me?. I made a prediction closeloop NarX, ie inputs have introduced today and given me the values of tomorrow. The problem is that when I look at the diagram in the original outputs (I do it for comparing the outputs with the outputs predicted original) gives me the answer 2 steps later. That is, if the original data make me a peak in January, I predicted outputs do in 3. I've thought about making remove delay, but I have a problem with the command since I required preparets arrays of inputs and targets of the same size after applying tonndata and I have the same dimensions as if tomorrow I get the targets, which now I have no inputs are the morning and therefore would not identical arrays. How I can solve the problem? thank you very much

Risposte (0)

Categorie

Scopri di più su Deep Learning Toolbox in Help Center e File Exchange

Tag

Community Treasure Hunt

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

Start Hunting!

Translated by