Training of neural networks using backpropagation, resilient backpropagation with (Riedmiller, 1994) or without weight backtracking (Riedmiller and Braun, 1993) or the modified globally convergent version by Anastasiadis et al. (2005). The package allows flexible settings through custom-choice of error and activation function. Furthermore, the calculation of generalized weights (Intrator O & Intrator N, 1993) is implemented.

Install the latest version of this package by entering the following in R:

`install.packages("neuralnet")`

Author | Stefan Fritsch [aut], Frauke Guenther [aut, cre], Marc Suling [ctb], Sebastian M. Mueller [ctb] |

Date of publication | 2016-08-16 12:08:44 |

Maintainer | Frauke Guenther <guenther@leibniz-bips.de> |

License | GPL (>= 2) |

Version | 1.33 |

**compute:** Computation of a given neural network for given covariate...

**confidence.interval:** Calculates confidence intervals of the weights

**gwplot:** Plot method for generalized weights

**neuralnet:** Training of neural networks

**neuralnet-package:** Training of Neural Networks

**plot.nn:** Plot method for neural networks

**prediction:** Summarizes the output of the neural network, the data and the...

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.

Embedding an R snippet on your website

Add the following code to your website.

For more information on customizing the embed code, read Embedding Snippets.