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: | 1.5 |
Imports: | Rcpp (≥ 0.12.12), robustbase (≥ 0.92), stats (≥ 3.3.2), graphics (≥ 3.3.2) |
LinkingTo: | Rcpp, RcppArmadillo |
Suggests: | rgl, reshape2 |
Published: | 2017-11-28 |
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 |
Reference manual: | ANN2.pdf |
Package source: | ANN2_1.5.tar.gz |
Windows binaries: | r-devel: ANN2_1.5.zip, r-release: ANN2_1.5.zip, r-oldrel: ANN2_1.5.zip |
OS X El Capitan binaries: | r-release: ANN2_1.5.tgz |
OS X Mavericks binaries: | r-oldrel: ANN2_1.5.tgz |
Old sources: | ANN2 archive |
Please use the canonical form https://CRAN.R-project.org/package=ANN2 to link to this page.