# -------------------------------------------- # CITATION file created with {cffr} R package # See also: https://docs.ropensci.org/cffr/ # -------------------------------------------- cff-version: 1.2.0 message: 'To cite package "innsight" in publications use:' type: software license: MIT title: 'innsight: Get the Insights of Your Neural Network' version: 0.3.1 doi: 10.18637/jss.v111.i08 identifiers: - type: doi value: 10.32614/CRAN.package.innsight - type: url value: https://github.com/bips-hb/innsight/ abstract: '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) , layer-wise relevance propagation (''LRP'') described by Bach et al. (2015) , deep learning important features (''DeepLIFT'') described by Shrikumar et al. (2017) and gradient-based methods like ''SmoothGrad'' described by Smilkov et al. (2017) , ''Gradient x Input'' or ''Vanilla Gradient''. Details can be found in the accompanying scientific paper: Koenen & Wright (2024, Journal of Statistical Software, ).' authors: - family-names: Koenen given-names: Niklas email: niklas.koenen@gmail.com orcid: https://orcid.org/0000-0002-4623-8271 preferred-citation: type: article title: Interpreting Deep Neural Networks with the Package innsight authors: - family-names: Koenen given-names: Niklas email: koenen@leibniz-bips.de orcid: https://orcid.org/0000-0002-4623-8271 - family-names: Wright given-names: Marvin N. email: wright@leibniz-bips.de journal: Journal of Statistical Software year: '2024' volume: '111' issue: '8' doi: 10.18637/jss.v111.i08 start: '1' end: '52' repository: https://CRAN.R-project.org/package=innsight repository-code: https://github.com/bips-hb/innsight/issues/ url: https://bips-hb.github.io/innsight/ date-released: '2024-11-26' contact: - family-names: Koenen given-names: Niklas email: niklas.koenen@gmail.com orcid: https://orcid.org/0000-0002-4623-8271