reconstruct

<p>logical indicating if Mahalanobis distance should be calculated</p>

mahalanobis

<p><code>reconstruct</code> takes new data as input and reconstructs the observations using
a trained replicator or autoencoder object.</p>

Training of general classification and regression neural networks using
gradient descent. Special features include a function for training replicator
neural networks and a function for training autoencoders. Multiple activation and
cost functions (including Huber and pseudo-Huber) are supported, as well as L1
and L2 regularization, momentum, early stopping and the possibility to specify
a learning rate schedule. The package contains a vectorized gradient descent
implementation which facilitates faster training through batch learning.

Bart Lammers

Last chance! 50% off unlimited learning

reconstruct: Reconstruct data using trained Autoencoder or Replicator object

Description

Usage

Arguments

Value

Details