neuralnet (1.44.2)

1 user

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: Marvin N. Wright
Author(s): Stefan Fritsch [aut], Frauke Guenther [aut], Marvin N. Wright [aut, cre], Marc Suling [ctb], Sebastian M. Mueller [ctb]

License: GPL (>= 2)

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

Released over 1 year ago.

6 previous versions



  3.0/5 (2 votes)


  3.0/5 (2 votes)

Log in to vote.


No one has written a review of neuralnet yet. Want to be the first? Write one now.

Related packages: AMORE, grnnR, nnet, monmlp, qrnn, RSNNS(20 best matches, based on common tags.)

Search for neuralnet on google, google scholar, r-help, r-devel.

Visit neuralnet on R Graphical Manual.