[HTML][HTML] What-if XAI framework (WiXAI): from counterfactuals towards causal understanding

N Kshetry, M Kantardzic - Journal of Computer and Communications, 2024 - scirp.org
People learn causal relations since childhood using counterfactual reasoning.
Counterfactual reasoning uses counterfactual examples which take the form of “what if this …

Optimal probabilistic feature shifts for reclassification in tree ensembles

V Blanco, A Japón, J Puerto, P Zhang - arXiv preprint arXiv:2412.03722, 2024 - arxiv.org
In this paper we provide a novel mathematical optimization based methodology to perturb
the features of a given observation to be re-classified, by a tree ensemble classification rule …

Grounding and Validation of Algorithmic Recourse in Real-World Contexts: A Systematized Literature Review

A Buszydlik, P Altmeyer, CCS Liem, R Dobbe - 2024 - openreview.net
The aim of algorithmic recourse (AR) is generally understood to be the provision of"
actionable" recommendations to individuals affected by algorithmic decision-making …

Interpretability of Neural Networks applied to Electrocardiograms: Translational Applications in Cardiovascular Diseases

A Fall - 2023 - theses.hal.science
Electrocardiograms (ECGs) are non-invasive tools for assessing the electrical activity of the
heart, they are widely used to detect cardiac abnormalities. Deep learning algorithms enable …

[引用][C] Studies on Explainable Machine Learning Based on Integer Linear Optimization

金森憲太朗 - 2022 - 北海道大学