Application of the Neural Network Dependability Kit in Real-World Environments

TL;DR

This paper demonstrates how the Neural Network Dependability Kit (NNDK) can be applied in real-world image classification tasks to improve model accuracy, robustness, and interpretability, especially in medical diagnosis support.

Contribution

It provides a practical guideline for using NNDK in development, showcasing its application in two case studies to enhance neural network trustworthiness and interpretability.

Findings

NNDK helps increase neural network accuracy and robustness.

It provides supporting evidence for classification results.

The approach aids medical professionals in interpreting AI decisions.

Abstract

In this paper, we provide a guideline for using the Neural Network Dependability Kit (NNDK) during the development process of NN models, and show how the algorithm is applied in two image classification use cases. The case studies demonstrate the usage of the dependability kit to obtain insights about the NN model and how they informed the development process of the neural network model. After interpreting neural networks via the different metrics available in the NNDK, the developers were able to increase the NNs' accuracy, trust the developed networks, and make them more robust. In addition, we obtained a novel application-oriented technique to provide supporting evidence for an NN's classification result to the user. In the medical image classification use case, it was used to retrieve case images from the training dataset that were similar to the current patient's image and could therefore act as a support for the NN model's decision and aid doctors in interpreting the results.