neuralnet (1.32)

Training of neural networks.

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.

Maintainer: Frauke Guenther
Author(s): Stefan Fritsch, Frauke Guenther <>, following earlier work by Marc Suling

License: GPL (>= 2)

Uses: MASS
Reverse depends: quarrint
Reverse suggests: caret, fscaret, mlr, NeuralNetTools, NeuralSens, nnetpredint, plotmo, shipunov, SPOT, vip

Released about 7 years ago.