Crandore Hub

innsight

Get the Insights of Your Neural Network

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>).

Versions across snapshots

VersionRepositoryFileSize
0.3.2 rolling linux/jammy R-4.5 innsight_0.3.2.tar.gz 2.4 MiB
0.3.2 rolling linux/noble R-4.5 innsight_0.3.2.tar.gz 2.4 MiB
0.3.2 rolling source/ R- innsight_0.3.2.tar.gz 1.8 MiB
0.3.2 latest source/ R- innsight_0.3.2.tar.gz 1.8 MiB
0.3.2 latest linux/jammy R-4.5 innsight_0.3.2.tar.gz 2.4 MiB
0.3.2 latest linux/noble R-4.5 innsight_0.3.2.tar.gz 2.4 MiB
0.3.2 2026-04-26 source/ R- innsight_0.3.2.tar.gz 1.8 MiB
0.3.2 2026-04-23 source/ R- innsight_0.3.2.tar.gz 1.8 MiB
0.3.2 2026-04-09 windows/windows R-4.5 innsight_0.3.2.zip 2.5 MiB
0.3.2 2025-04-20 source/ R- innsight_0.3.2.tar.gz 1.8 MiB

Dependencies (latest)

Imports

Suggests