nntrf: Supervised Data Transformation by Means of Neural Network Hidden Layers

A supervised transformation of datasets is performed. The aim is similar to that of Principal Component Analysis (PCA), that is, to carry out data transformation and dimensionality reduction, but in a non-linear supervised way. This is achieved by first training a 3-layer Multi-Layer Perceptron and then using the activations of the hidden layer as a transformation of the input features. In fact, it takes advantage of the change of representation provided by the hidden layer of a neural network. This can be useful as data pre-processing for Machine Learning methods in general, specially for those that do not work well with many irrelevant or redundant features. Rumelhart, D.E., Hinton, G.E. and Williams, R.J. (1986) "Learning representations by back-propagating errors" <doi:10.1038/323533a0>.

Version: 0.1.0
Depends: R (≥ 3.2.4)
Imports: nnet, NeuralNetTools, FNN, pracma
Suggests: dplyr, knitr, rmarkdown, ggplot2, ggridges, tidyr, forcats
Published: 2020-06-04
Author: Ricardo Aler [aut, cre], Jose Valls [aut]
Maintainer: Ricardo Aler <ricardo.aler at uc3m.es>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
Materials: README NEWS
CRAN checks: nntrf results

Downloads:

Reference manual: nntrf.pdf
Vignettes: nntrf
Package source: nntrf_0.1.0.tar.gz
Windows binaries: r-devel: nntrf_0.1.0.zip, r-release: nntrf_0.1.0.zip, r-oldrel: nntrf_0.1.0.zip
macOS binaries: r-release: nntrf_0.1.0.tgz, r-oldrel: nntrf_0.1.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=nntrf to link to this page.