Add sparsity regularization to an autoencoder

make_sparse(learner, high_probability = 0.1, weight = 0.2)

Arguments

learner

A "ruta_autoencoder" object

high_probability

Expected probability of the high value of the encoding layer. Set this to a value near zero in order to minimize activations in that layer.

weight

The weight of the sparsity regularization

Value

The same autoencoder with the sparsity regularization applied

See also