to_keras.ruta_sparsity

<p>Name of the activation function used in the encoding layer</p>

activation

<p>Translate sparsity regularization to Keras regularizer</p>

Implementation of several unsupervised neural networks,
from building their architecture to their training and evaluation. Available
networks are auto-encoders including their main variants: sparse, contractive,
denoising, robust and variational, as described in Charte et al. (2018)
<doi:10.1016/j.inffus.2017.12.007>.

David Charte

ruta

to_keras.ruta_sparsity: Translate sparsity regularization to Keras regularizer

Description

Usage

Arguments

Value

References