Interpretation methods for analyzing the behavior and individual predictions of modern neural networks in a three-step procedure: Converting the model, running the interpretation method, and visualizing the results. Implemented methods are, e.g., '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) <doi:10.48550/arXiv.1704.02685> and gradient-based methods like 'SmoothGrad' described by Smilkov et al. (2017) <doi:10.48550/arXiv.1706.03825>, 'Gradient x Input' described by Baehrens et al. (2009) <doi:10.48550/arXiv.0912.1128> or 'Vanilla Gradient'.
Version: | 0.3.0 |
Depends: | R (≥ 3.5.0) |
Imports: | checkmate, cli, ggplot2, methods, R6, torch |
Suggests: | covr, fastshap, GGally, grid, gridExtra, gtable, keras, knitr, lime, luz, neuralnet, palmerpenguins, plotly, rmarkdown, ranger, spelling, tensorflow, testthat (≥ 3.0.0) |
Published: | 2023-12-21 |
DOI: | 10.32614/CRAN.package.innsight |
Author: | Niklas Koenen [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 |
Language: | en-US |
Materials: | README NEWS |
CRAN checks: | innsight results |
Reference manual: | innsight.pdf |
Vignettes: |
Example 1: Iris dataset with torch Example 2: Penguin dataset with torch and luz In-depth explanation Introduction to innsight |
Package source: | innsight_0.3.0.tar.gz |
Windows binaries: | r-devel: innsight_0.3.0.zip, r-release: innsight_0.3.0.zip, r-oldrel: innsight_0.3.0.zip |
macOS binaries: | r-release (arm64): innsight_0.3.0.tgz, r-oldrel (arm64): innsight_0.3.0.tgz, r-release (x86_64): innsight_0.3.0.tgz, r-oldrel (x86_64): innsight_0.3.0.tgz |
Old sources: | innsight archive |
Please use the canonical form https://CRAN.R-project.org/package=innsight to link to this page.