ANN2: 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.

Version: 1.3
Imports: Rcpp (≥ 0.12.12), robustbase (≥ 0.92), stats (≥ 3.3.2), graphics (≥ 3.3.2)
LinkingTo: Rcpp, RcppArmadillo
Suggests: rgl, reshape2
Published: 2017-11-16
Author: Bart Lammers
Maintainer: Bart Lammers <bart.f.lammers at gmail.com>
License: GPL (≥ 3)
URL: https://github.com/bflammers/ANN2
NeedsCompilation: yes
CRAN checks: ANN2 results

Downloads:

Reference manual: ANN2.pdf
Package source: ANN2_1.3.tar.gz
Windows binaries: r-devel: ANN2_1.1.zip, r-release: ANN2_1.1.zip, r-oldrel: ANN2_1.3.zip
OS X El Capitan binaries: r-release: ANN2_1.3.tgz
OS X Mavericks binaries: r-oldrel: ANN2_1.3.tgz
Old sources: ANN2 archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=ANN2 to link to this page.