hardlim returns 0.5 and 1 !!
1 Ansicht (letzte 30 Tage)
Ältere Kommentare anzeigen
Morteza
am 27 Mär. 2019
Beantwortet: Garrett Beard
am 3 Dez. 2021
I have a binarry classification problem with 0-1 classes. I used 3layered neural network with "hardlim" as the activation function of output layer and "tansig" for hidden and input layer. I am wonderfull why my predicted output contains 0.5 and 1 instead of 0-1 !!
Does MATLAB automatically normalizes data when we use it's standard function for NN? Or I should manually normalize data?
5 Kommentare
Akzeptierte Antwort
Garrett Beard
am 3 Dez. 2021
'net variable'.output.processFcns = {}
By default, the neural network class applies mapminmax to the output vector. Remove the normalization and you will get [0, 1] for outputs.
0 Kommentare
Weitere Antworten (0)
Siehe auch
Kategorien
Mehr zu Define Shallow Neural Network Architectures 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!