Interpreting Deep Neural Networks with the Package innsight

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Koenen, Niklas, Wright, Marvin N.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910788605706240
author Koenen, Niklas
Wright, Marvin N.
author_facet Koenen, Niklas
Wright, Marvin N.
contents The R package innsight offers a general toolbox for revealing variable-wise interpretations of deep neural networks' predictions with so-called feature attribution methods. Aside from the unified and user-friendly framework, the package stands out in three ways: It is generally the first R package implementing feature attribution methods for neural networks. Secondly, it operates independently of the deep learning library allowing the interpretation of models from any R package, including keras, torch, neuralnet, and even custom models. Despite its flexibility, innsight benefits internally from the torch package's fast and efficient array calculations, which builds on LibTorch $-$ PyTorch's C++ backend $-$ without a Python dependency. Finally, it offers a variety of visualization tools for tabular, signal, image data or a combination of these. Additionally, the plots can be rendered interactively using the plotly package.
format Preprint
id arxiv_https___arxiv_org_abs_2306_10822
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Interpreting Deep Neural Networks with the Package innsight
Koenen, Niklas
Wright, Marvin N.
Machine Learning
The R package innsight offers a general toolbox for revealing variable-wise interpretations of deep neural networks' predictions with so-called feature attribution methods. Aside from the unified and user-friendly framework, the package stands out in three ways: It is generally the first R package implementing feature attribution methods for neural networks. Secondly, it operates independently of the deep learning library allowing the interpretation of models from any R package, including keras, torch, neuralnet, and even custom models. Despite its flexibility, innsight benefits internally from the torch package's fast and efficient array calculations, which builds on LibTorch $-$ PyTorch's C++ backend $-$ without a Python dependency. Finally, it offers a variety of visualization tools for tabular, signal, image data or a combination of these. Additionally, the plots can be rendered interactively using the plotly package.
title Interpreting Deep Neural Networks with the Package innsight
topic Machine Learning
url https://arxiv.org/abs/2306.10822