The interpretation of feature importance in machine learning models is challenging when
features are dependent. Permutation feature importance (PFI) ignores such dependencies …

The term robustness is ubiquitous in modern Machine Learning (ML). However, its meaning
varies depending on context and community. Researchers either focus on narrow technical …

Scientists and practitioners increasingly rely on machine learning to model data and draw
conclusions. Compared to statistical modeling approaches, machine learning makes fewer …

Despite progress in the field, significant parts of current XAI research are still not on solid
conceptual, ethical, or methodological grounds. Unfortunately, these unfounded parts are …

We propose a non-representationalist framework for deep learning relying on a novel
method computational phenomenology, a dialogue between the first-person perspective …

Artificial intelligence (AI) is currently based largely on black-box machine learning models
which lack interpretability. The field of eXplainable AI (XAI) strives to address this major …

In this paper, we examine gradients of logits of image classification CNNs by input pixel
values. We observe that these fluctuate considerably with training randomness, such as the …

Global feature effect methods, such as partial dependence plots, provide an intelligible
visualization of the expected marginal feature effect. However, such global feature effect …

Scientists frequently prioritize learning from data rather than training the best possible
model; however, research in machine learning often prioritizes the latter. Marginal …

This work aims to provide profound insights into neural networks and deep learning,
focusing on their functioning, interpretability, and generalization capabilities. It explores …