I don't understand why both notions have different values
1 Ansicht (letzte 30 Tage)
Ältere Kommentare anzeigen
I quote this from Matlab autoencoder help:
"Example: 'SparsityProportion',0.01 is equivalent to saying that each neuron in the hidden layer should have an average output of 0.1 over the training examples."
How is the average activation(0.1) related to the Sparsity proportion (0.01) ?
I don't understand why the average activation equals 0.1. I thought it should be 0.01
0 Kommentare
Antworten (0)
Siehe auch
Kategorien
Mehr zu Install Products 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!