Creating N number of outputs for Neural Network
1 Ansicht (letzte 30 Tage)
Ältere Kommentare anzeigen
Hello,
This is more of a confirmation rather than a question because whenever I tried to find the solution on the question forums, there were no thourough answers explaining in detail what I needed. So here we go:
If you are trying to create a neural network with N number of outputs using the feedforwardnet tool, the labels/target needs to have the demensionality of N columns. Meaning, that if my neural network wants to have 7 outputs and I have a 100x12 training data set (100 being # of patients with 12 features) with a 100x1 label/target dataset (over the 100 rows, there's 7 different labels say 1-7 or however you classified them), you need to change the label dataset/matrix into a 100x7. I realized on my own that the number of outputs are dependent on the number of columns there are in the label/target matrix.
0 Kommentare
Antworten (0)
Siehe auch
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!