Results 151 to 160 of about 941 (218)

User‐Based Evaluation of Explainability Techniques for Misogyny Detection in Code‐Mixed Hindi–English

open access: yesApplied AI Letters, Volume 7, Issue 2, June 2026.
In this work, we have performed human‐based evaluation of three post hoc explainability techniques, Local Interpretable Model Agnostic Explanations (LIME), Shapely Additive Explanations (SHAP), and integrated Gradients (IG) for a multilingual Bidirectional Encoder Representations from Transformers (mBERT) based binary and multi‐label misogyny ...
Sargam Yadav   +2 more
wiley   +1 more source

Cross‐Method Explanation Stability Under Prediction‐Preserving Perturbations in Explainable AI

open access: yesApplied AI Letters, Volume 7, Issue 2, June 2026.
The cross‐method analysis showed common vulnerability patterns across gradient‐based and perturbation‐based explainers, whereas Grad‐CAM demonstrated a specific ability to be resilient. Further discussion revealed that, before prediction changes with increasing ε, explanation divergence could already have commenced, indicating that further explanation ...
Muhammad Hasnain   +4 more
wiley   +1 more source

Evidence for direct and sleep‐moderated relationships between aquaporin‐4 genetic variants and Alzheimer's disease phenotypes

open access: yesAlzheimer's &Dementia, Volume 22, Issue 6, June 2026.
Abstract INTRODUCTION Variants in the aquaporin‐4 gene (AQP4) have been associated with Alzheimer's disease (AD) diagnosis, cognition, and brain amyloid beta (Aβ) and may affect the sleep and Aβ relationship. Their association with other AD‐related phenotypes/disease progression remain largely unknown.
Tenielle Porter   +12 more
wiley   +1 more source

Sex differences in the association of adverse childhood experiences with brain and cognition along a continuum of risk for Alzheimer's disease

open access: yesAlzheimer's &Dementia, Volume 22, Issue 6, June 2026.
Abstract INTRODUCTION Women make up two‐thirds of people with Alzheimer's disease (AD). Research has focused on biological explanations for this sex difference, while contributions of psychosocial risk factors are less well understood. METHODS We examined sex differences in the effects of adverse childhood experiences (ACEs) on late‐life cognition in ...
Mateja Perović   +2 more
wiley   +1 more source

Non‐negative Gaussian estimation of variance components in random effects models

open access: yesCanadian Journal of Statistics, Volume 54, Issue 2, June 2026.
Abstract When used to estimate variance components (VCs), confidence intervals (CIs) can be truncated at zero, have a point estimate not in the quoted CI, be empty with positive probability, or be all‐inclusive. This is because they have conflicting dual roles, since they are considered to cover the parameter with a specified probability while also ...
André Plante, Michael Plante
wiley   +1 more source

Home - About - Disclaimer - Privacy