reconstruction_plot

reconstruction_plot.ANN

autoencoder object of class <code>ANN</code>

object

&#8230;

data matrix with original values to be reconstructed and plotted

optional vector of discrete colors. The reconstruction errors
are are used as color if this argument is not specified

colors

plots original and reconstructed data points in a single plot with connecting 
lines between original value and corresponding reconstruction

Training of neural networks for classification and regression tasks
using mini-batch gradient descent. Special features include a function for
training autoencoders, which can be used to detect anomalies, and some
related plotting functions. Multiple activation functions are supported,
including tanh, relu, step and ramp. For the use of the step and ramp
activation functions in detecting anomalies using autoencoders, see
Hawkins et al. (2002) <doi:10.1007/3-540-46145-0_17>. Furthermore,
several loss functions are supported, including robust ones such as Huber
and pseudo-Huber loss, as well as L1 and L2 regularization. The possible
options for optimization algorithms are RMSprop, Adam and SGD with momentum.
The package contains a vectorized C++ implementation that facilitates
fast training through mini-batch learning.

reconstruction_plot: Reconstruction plot

Description

Usage

Arguments

Value

Details