Interpreting Deep Neural Networks with the Package innsight

Interpreting Deep Neural Networks with the Package innsight

neural networks, feature attribution, interpretable machine learning, explainable
artificial intelligence, XAI, IML, torch, keras, R.

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 neural networks 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.

Niklas Koenen

Leibniz Institute for Prevention
Research and Epidemiology – BIPS,
University of Bremen

Leibniz Institute for Prevention
Research and Epidemiology – BIPS,
University of Bremen

November 2024

Fajar bagus W

PDF

English

Text