Tag: model interpretability

A standardized benchmark of six convolutional neural networks shows that the most accurate pneumonia-detecting models also produce the most faithful ...

A new framework called ARCHEX uses archetypal analysis to reveal global structural patterns in machine learning models that local explanation ...

A new study shows that popular AI explanation methods produce nearly identical heatmaps for different class labels, and introduces CASE, ...

Researchers have developed CausalCACTUS, a framework that generates counterfactual explanations for black-box machine learning models which simultaneously respect learned causal ...

A comprehensive new review maps the technical, regulatory, and ethical barriers separating deep learning breakthroughs in medical imaging from safe ...

A new framework called EKT-XAI processes 95 million student interactions in minutes using a lightweight transformer that matches deep knowledge ...