sparsity

<p>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.</p>

high_probability

<p>The weight of the sparsity regularization</p>

weight

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

sparsity: Sparsity regularization

Description

Usage

Arguments

Value

References

See Also