Type: Package
Package: innsight
Title: Get the Insights of Your Neural Network
Version: 0.3.2.9000
Authors@R: c(
    person("Niklas", "Koenen", , "niklas.koenen@gmail.com", role = c("aut", "cre"),
           comment = c(ORCID = "0000-0002-4623-8271")),
    person("Raphael", "Baudeu", , "raphael.baudeu@gmail.com", role = "ctb")
  )
Description: 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' or 'Vanilla
        Gradient'. Details can be found in the accompanying scientific
        paper: Koenen & Wright (2024, Journal of Statistical Software,
        <doi:10.18637/jss.v111.i08>).
License: MIT + file LICENSE
URL: https://bips-hb.github.io/innsight/,
        https://github.com/bips-hb/innsight/
BugReports: https://github.com/bips-hb/innsight/issues/
Depends: R (>= 3.5.0)
Imports: checkmate, cli, ggplot2, methods, R6, torch
Suggests: covr, fastshap, GGally, grid, gridExtra, gtable, keras,
        keras3, knitr, lime, luz, neuralnet, palmerpenguins, plotly,
        rmarkdown, ranger, spelling, tensorflow, testthat (>= 3.0.0)
VignetteBuilder: knitr
Config/testthat/edition: 3
Encoding: UTF-8
Language: en-US
Roxygen: list(markdown = TRUE, r6 = TRUE)
RoxygenNote: 7.3.3
Collate: 'AgnosticMethods.R' 'AgnosticWrapper.R' 'ConnectionWeights.R'
        'Convert_keras.R' 'Convert_neuralnet.R' 'Convert_torch.R'
        'ConvertedModel.R' 'Converter.R' 'DeepLift.R' 'GradienBased.R'
        'torch_gradients.R' 'InterpretingLayer.R'
        'InterpretingMethod.R' 'LRP.R' 'Layer_conv1d.R'
        'Layer_conv2d.R' 'Layer_dense.R' 'Layer_normalization.R'
        'Layer_other.R' 'Layer_pooling.R' 'innsight.R' 'utils.R'
        'utils_ggplot.R' 'utils_plotly.R' 'innsight_sugar.R'
        'innsight_ggplot2.R' 'innsight_plotly.R'
Repository: https://bips-hb.r-universe.dev
Date/Publication: 2026-02-22 19:18:08 UTC
RemoteUrl: https://github.com/bips-hb/innsight
RemoteRef: HEAD
RemoteSha: bc63149b2b97bb33979f77c677ef009277d3e132
NeedsCompilation: no
Packaged: 2026-06-22 10:02:34 UTC; root
Author: Niklas Koenen [aut, cre] (ORCID:
    <https://orcid.org/0000-0002-4623-8271>),
  Raphael Baudeu [ctb]
Maintainer: Niklas Koenen <niklas.koenen@gmail.com>