to_keras.ruta_sparsity: Translate sparsity regularization to Keras regularizer

In ruta: Implementation of Unsupervised Neural Architectures

Translate sparsity regularization to Keras regularizer

Description

Translate sparsity regularization to Keras regularizer

Usage

## S3 method for class 'ruta_sparsity'
to_keras(x, activation, ...)

Arguments

x	Sparsity object
activation	Name of the activation function used in the encoding layer
...	Unused

Value

Function which can be used as activity regularizer in a Keras layer

References

• Sparse deep belief net model for visual area V2

• Andrew Ng, Sparse Autoencoder. CS294A Lecture Notes (2011)

ruta documentation built on Jan. 9, 2023, 1:20 a.m.