innsight: Get the Insights of your Neural Network

Interpretability methods to analyze the behavior and individual predictions of modern neural networks. Implemented methods are: 'Connection Weights' described by Olden et al. (2004) <doi:10.1016/j.ecolmodel.2004.03.013>, Layer-wise Relevance Propagation ('LRP') described by Bach et al. (2015) <doi:10.1371/journal.pone.0130140>, Deep Learning Important Features ('DeepLIFT') described by Shrikumar et al. (2017) <arXiv:1704.02685> and gradient-based methods like 'SmoothGrad' described by Smilkov et al. (2017) <arXiv:1706.03825>, 'Gradient x Input' described by Baehrens et al. (2009) <arXiv:0912.1128> or 'Vanilla Gradient'.

Version: 0.1.0
Depends: R (≥ 3.5.0)
Imports: checkmate, ggplot2, R6, torch
Suggests: keras, knitr, neuralnet, plotly, rmarkdown, tensorflow, testthat (≥ 3.0.0)
Published: 2021-11-22
Author: Niklas Koenen ORCID iD [aut, cre], Raphael Baudeu [ctb]
Maintainer: Niklas Koenen <niklas.koenen at gmail.com>
BugReports: https://github.com/bips-hb/innsight/issues/
License: MIT + file LICENSE
URL: https://bips-hb.github.io/innsight/, https://github.com/bips-hb/innsight/
NeedsCompilation: no
Materials: README NEWS
CRAN checks: innsight results

Documentation:

Reference manual: innsight.pdf
Vignettes: Custom Model Definition
Introduction to innsight

Downloads:

Package source: innsight_0.1.0.tar.gz
Windows binaries: r-devel: innsight_0.1.0.zip, r-release: innsight_0.1.0.zip, r-oldrel: innsight_0.1.0.zip
macOS binaries: r-release (arm64): innsight_0.1.0.tgz, r-release (x86_64): innsight_0.1.0.tgz, r-oldrel: innsight_0.1.0.tgz

Linking:

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