Interpreting Deep Neural Networks with the Package innsight

TL;DR

The innsight R package provides a versatile, library-agnostic toolkit for interpreting deep neural networks through feature attribution methods, with interactive visualizations for various data types.

Contribution

It is the first R package to implement feature attribution methods for neural networks, supporting models from multiple libraries without Python dependencies.

Findings

Supports models from keras, torch, neuralnet, and custom sources

Offers interactive visualizations with plotly

Operates independently of deep learning libraries

Abstract

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.