Explainable artificial intelligence (XAI) methods are portrayed as a remedy for debugging
and trusting statistical and deep learning models, as well as interpreting their predictions …

The past decade has seen significant progress in artificial intelligence (AI), which has
resulted in algorithms being adopted for resolving a variety of problems. However, this …

Artificial intelligence (AI) is having a growing impact in many areas related to drug discovery.
However, it is still critical for their adoption by the medicinal chemistry community to achieve …

Understanding black box models has become paramount as systems based on opaque
Artificial Intelligence (AI) continue to flourish in diverse real-world applications. In response …

Deep learning models like chatGPT exemplify AI success but necessitate a deeper
understanding of trust in critical sectors. Trust can be achieved using counterfactual …

Abstract Although Deep Neural Networks (DNNs) have great generalization and prediction
capabilities, their functioning does not allow a detailed explanation of their behavior …

Artificial Intelligence (AI) is becoming fundamental in almost all activity sectors in our society.
However, most of the modern AI techniques (eg, Machine Learning–ML) have a black box …

Prototypical part neural networks (ProtoPartNNs), namely ProtoPNet and its derivatives, are
an intrinsically interpretable approach to machine learning. Their prototype learning scheme …

Introduction Machine learning research into automated dementia diagnosis is becoming
increasingly popular but so far has had limited clinical impact. A key challenge is building …

We explore the integration of domain knowledge graphs into Deep Learning for improved
interpretability and explainability using Graph Neural Networks (GNNs). Specifically, a …