input

<p>This layer acts as a placeholder for input data. The number of units is not
needed as it is deduced from the data during training.</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

Implementation of Unsupervised Neural Architectures

input: Create an input layer

Description

Usage

Arguments

Value

See Also