predict.ANN

object

newdata

<p><code>predict</code> Predict class or value for new data</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

predict.ANN: Make predictions for new data

Description

Usage

Arguments

Value

Details