Learn R Programming

⚠️There's a newer version (2.3.4) of this package.Take me there.

ANN2 (version 1.2)

Artificial Neural Networks for Anomaly Detection

Description

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.

Copy Link

Version

Install

install.packages('ANN2')

Monthly Downloads

580

Version

1.2

License

GPL (>= 3)

Issues

Pull Requests

Stars

Forks

Maintainer

Bart Lammers

Last Published

November 15th, 2017

Functions in ANN2 (1.2)

neuralnetwork

Train a Neural Network
plot.ANN

Plot training and validation loss
plot.rANN

Plot mahalanobis distances of reconstructed errors
reconstruct

Reconstruct data using trained Autoencoder or Replicator object
plotStepFunction

Plot the step function used in replicator
replicator

Train a Replicator Neural Network
autoencoder

Train an Autoencoding Neural Network
predict.ANN

Make predictions for new data
example_NN

Visual examples of training a Neural Network
print.ANN

Print ANN