How Does Matlab Neural Network Toolbox Preprocess Data?

3 Ansichten (letzte 30 Tage)
Christian Kruschel
Christian Kruschel am 5 Sep. 2016
Beantwortet: Greg Heath am 6 Sep. 2016
I try to analyse my neural network trained via Neural Network Toolbox and Matlab 2016a. I was wondering how Matlab preprocesses data. I tried the following: X = -1:.1:1, Y = purelin(2*tansig(X) + tanig(X) -2) and trained a Feedforward Net, lets call it "net", with one hidden Layer and two neurons with tansig activations. I thought net(X(k)) is the same as purelin(net.LW{2,1}*tansig(net.IW{1}*X(k)-net.b{1})-net.b{2}) for any feasible index k, but this is not right. What did I do wrong or is there some hidden preprocessing?
Thanks for any answer!

Antworten (1)

Greg Heath
Greg Heath am 6 Sep. 2016
You forgot the default input and target normalization with MAPMINMAX followed by the output denormalization.
Hope this helps.
Thank you for formally accepting my answer
Greg

Kategorien

Mehr zu Deep Learning Toolbox finden Sie in Help Center und File Exchange

Community Treasure Hunt

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

Start Hunting!

Translated by