ANN2 (1.3)

Artificial Neural Networks for Anomaly Detection.

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.

Maintainer: Bart Lammers
Author(s): Bart Lammers

License: GPL (>= 3)

Uses: Rcpp, robustbase, rgl, reshape2

Released about 2 years ago.