Clear Filters
Clear Filters

I don't understand why both notions have different values

1 view (last 30 days)
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

Answers (0)

Categories

Find more on Install Products in Help Center and File Exchange

Community Treasure Hunt

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

Start Hunting!