Hidden_l1 problem
jamona opened this issue · comments
If I don't specify a certain layer for the hidden_l1 restriction with dict() it won't apply the regularization (therefore error = loss all the time). Are there any news on this issue?
That's what climate says, after applying hidden_sparsity=0.95 to the train function: theanets.regularizers:160 regularizer: 0.95 * HiddenL1(None)