Results 91 to 100 of about 20,583 (298)

Explainable Artificial Intelligence (XAI)

, 2022
The field of explainable artificial intelligence (XAI) advances techniques, processes, and strategies that provide explanations for the predictions, recommendations, and decisions of opaque and complex machine learning systems.
Michael Ridley, Ridley, Michael
core   +1 more source

Explainable AI‐Driven Optimization of Electrode Activation Reduces Power Consumption While Preserving Object Recognition in Retinal Prostheses

Advanced Intelligent Systems, EarlyView.
Explainable artificial intelligence (XAI) guides selective electrode activation in retinal prostheses by emphasizing visually informative regions. XAI‐assisted phosphene generation maintains object recognition performance while significantly reducing stimulation power.
Sein Kim, Hamin Shim, Maesoon Im
wiley   +1 more source

XAI and Digital Competence

, 2022
This project aims to investigate how explainable AI (XAI) can promote adequate levels of user digital competence so users can cope with AI-driven communication, including three sup-projects that build on each other 1) users’ current levels of AI literacy
Judith Moeller, Sophie C. Boerman, Claes de Vreese, Chenyue Wang   +3 more
core   +1 more source

Shapley Additive Explanation for Local Class Differentiation: Local Explainability for Class Differentiation in Classification Models

Advanced Intelligent Systems, EarlyView.
An instance‐level, model‐agnostic explanation of class differentiation is introduced through SHAP‐LCD, linking probability shifts to feature‐wise Shapley contributions. The method operates on tabular and image data and is released in a fully reproducible implementation, offering a transparent way to examine, at each instance, why predictive models ...
Roxana M. Romero Luna, Hugo A. Ordoñez Erazo, Carlos A. Cobos Lozada   +2 more
wiley   +1 more source

Improvements in Patient‐Reported Outcomes and Few Reported Major Complications Following Hip Arthroscopy in Patients With Femoroacetabular Impingement Syndrome: A Systematic Review

Arthroscopy, Sports Medicine, and Rehabilitation, EarlyView.
Purpose To systematically review the literature to evaluate complications and patient‐reported outcome measures (PROMs) after hip arthroscopy in patients with femoroacetabular impingement syndrome. Methods Five databases were searched for studies reporting complications and PROMs after hip arthroscopy in patients with femoroacetabular impingement ...
Frederik Nicolai Foldager, Julius David, Lisa Urup Tønning, Bjarne Mygind‐Klavsen, Christian Gatzka, Barbara Zimmerman, Inger Mechlenburg   +6 more
wiley   +1 more source

/xai/xai School; Outdoor Class Older Grades

, 1980
/xai/xai ...
Lee, Richard B.
core   +1 more source

Performance of multimodal large language models on image‐based surgical anatomy, anatomical pathology, and radiology questions

Anatomical Sciences Education, EarlyView.
Abstract Multimodal large language models (LLMs) are now deeply integrated into medical education and widely used by medical students, yet it remains unclear whether current models possess the accuracy and reliability needed to support image‐based learning.
Ming Lu, Josiah Cheng, Vinod Gopalan
wiley   +1 more source

Detecting Ineffective Efforts during Expiration for Neonates with Attention RNNs

Current Directions in Biomedical Engineering
Patient-ventilator asynchronies occur during mechanical ventilation when there is a mismatch between the patient’s needs and the ventilator’s settings.
Oprea Camelia, Stegemann Lara, Olivier Lena Sophie, Buglowski Mateusz, Becker Sabine, Orlikowsky Thorsten, Kowalewski Stefan, Schoberer Mark, Stollenwerk André   +8 more
doaj   +1 more source

XAI for network management

pub
Fiandrino, Claudio, Fernández, Pablo, Fiore, Marco, Widmer, Joerg   +3 more
openaire   +2 more sources

Overcoming Catastrophic Forgetting by XAI

CoRR, 2022
Explaining the behaviors of deep neural networks, usually considered as black boxes, is critical especially when they are now being adopted over diverse aspects of human life. Taking the advantages of interpretable machine learning (interpretable ML), this work proposes a novel tool called Catastrophic Forgetting Dissector (or CFD) to explain ...
openaire   +2 more sources