NeuralSens: Sensitivity Analysis of Neural Networks

Analysis functions to quantify inputs importance in neural network models. Functions are available for calculating and plotting the inputs importance and obtaining the activation function of each neuron layer and its derivatives. The importance of a given input is defined as the distribution of the derivatives of the output with respect to that input in each training data point <doi:10.18637/jss.v102.i07>.

Version: 1.1.3
Imports: ggplot2, gridExtra, NeuralNetTools, reshape2, caret, fastDummies, stringr, Hmisc, ggforce, scales, ggnewscale, magrittr, ggrepel, ggbreak, dplyr
Suggests: h2o, RSNNS, nnet, neuralnet, plotly, e1071
Published: 2024-05-11
DOI: 10.32614/CRAN.package.NeuralSens
Author: José Portela González [aut], Antonio Muñoz San Roque [aut], Jaime Pizarroso Gonzalo [aut, ctb, cre]
Maintainer: Jaime Pizarroso Gonzalo <jpizarroso at>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
Citation: NeuralSens citation info
CRAN checks: NeuralSens results


Reference manual: NeuralSens.pdf


Package source: NeuralSens_1.1.3.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): NeuralSens_1.1.3.tgz, r-oldrel (arm64): NeuralSens_1.1.3.tgz, r-release (x86_64): NeuralSens_1.1.3.tgz, r-oldrel (x86_64): NeuralSens_1.1.3.tgz
Old sources: NeuralSens archive


Please use the canonical form to link to this page.