Explainable Artificial Intelligence (XAI) has experienced a significant growth over the last few
years. This is due to the widespread application of machine learning, particularly deep …

Machine and deep learning have proven their utility to generate data-driven models with
high accuracy and precision. However, their non-linear, complex structures are often difficult …

After building a classifier with modern tools of machine learning we typically have a black
box at hand that is able to predict well for unseen data. Thus, we get an answer to the …

Using artificial intelligence (AI) technology to replace human decision-making will inevitably
create new risks whose consequences are unforeseeable. This naturally leads to calls for …

Local additive explanation methods are increasingly used to understand the predictions of
complex Machine Learning (ML) models. The most used additive methods, SHAP and LIME …

Abstract As Machine Learning (ML) is now widely applied in many domains, in both
research and industry, an understanding of what is happening inside the black box is …

Local additive explanation methods are increasingly used to understand the predictions of
complex Machine Learning (ML) models. The most used additive methods, SHAP and LIME …

Background The human microbiota is associated with various disease states and holds a
great promise for non-invasive diagnostics. However, microbiota data is challenging for …

In this paper, we describe the first practical application of two methods, which bridge the gap
between the non-expert user and machine learning models. The first is a method for …

Background Machine learning models that are used for predicting clinical outcomes can be
made more useful by augmenting predictions with simple and reliable patient-specific …