Motivation: We explored how explainable AI (XAI) can help to shed light ...
Deep learning has emerged as the preferred modeling approach for automat...
Deep neural networks have become increasingly popular for analyzing ECG ...
Feature importance methods promise to provide a ranking of features acco...
The completeness axiom renders the explanation of a post-hoc XAI method ...
Synthetic data generation is a promising solution to address privacy iss...
The field of deep-learning-based ECG analysis has been largely dominated...
The imputation of missing values represents a significant obstacle for m...
Concepts are key building blocks of higher level human understanding.
Ex...
There is an increasing number of medical use-cases where classification
...
Predicting the binding of viral peptides to the major histocompatibility...
We put forward a comprehensive assessment of self-supervised representat...
PredDiff is a model-agnostic, local attribution method that is firmly
ro...
Generative neural samplers offer a complementary approach to Monte Carlo...
Electrical impedance tomography (EIT) is a noninvasive imaging modality ...
Electrocardiography is a very common, non-invasive diagnostic procedure ...
Machine learning has the potential to aid our understanding of phase
str...
We propose a general framework for the estimation of observables with
ge...
We study the recently introduced stability training as a general-purpose...
In this comment on "Solving Statistical Mechanics Using Variational
Auto...
We investigate Early Hybrid Automatic Repeat reQuest (E-HARQ) feedback
s...
We consider the detection of myocardial infarction in electrocardiograph...