The rising popularity of explainable artificial intelligence (XAI) to understand high-performing
black boxes raised the question of how to evaluate explanations of machine learning (ML) …

The rise in deep neural networks (DNNs) has led to increased interest in explaining their
predictions. While many methods for this exist, there is currently no consensus on how to …

Unsupervised representation learning has proved to be a critical component of anomaly
detection/localization in images. The challenges to learn such a representation are two-fold …

Deep neural networks (DNNs) are an indispensable machine learning tool despite the
difficulty of diagnosing what aspects of a model's input drive its decisions. In countless real …

Machine-learning models have demonstrated great success in learning complex patterns
that enable them to make predictions about unobserved data. In addition to using models for …

Saliency methods have emerged as a popular tool to highlight features in an input deemed
relevant for the prediction of a learned model. Several saliency methods have been …

Graph neural networks (GNNs) have become a popular approach to integrating structural
inductive biases into NLP models. However, there has been little work on interpreting them …

Deep Learning is a state-of-the-art technique to make inference on extensive or complex
data. As a black box model due to their multilayer nonlinear structure, Deep Neural …

Purpose To evaluate the trustworthiness of saliency maps for abnormality localization in
medical imaging. Materials and Methods Using two large publicly available radiology …

A critical problem in the field of post hoc explainability is the lack of a common foundational
goal among methods. For example, some methods are motivated by function approximation …