Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
XAI for U 2025: 2$nd$ International Workshop on Explainable AI for Ubiquitous, Pervasive and Wearable Computing
0
Zitationen
5
Autoren
2025
Jahr
Abstract
The workshop XAI for U aims to address the critical need for transparency in Artificial Intelligence (AI) systems that are increasingly integrated into our daily lives through mobile systems, wearables, and smart environments. Despite rapid advances in AI and machine learning, many of these systems remain opaque, making it difficult for users, designers, developers, and stakeholders to verify their reliability, fairness, and correctness. This lack of transparency can hinder trust, informed decision-making, and broader adoption. This workshop focuses on the pressing need to enable Explainable AI (XAI) tools tailored for ubiquitous, pervasive, and wearable computing, and highlights the unique challenges associated with this domain, such as generating explanations for time-series and multimodal data, interpreting interconnected machine learning components, and delivering user-centered explanations. It aims to foster interdisciplinary collaboration among researchers across related domains, share recent advancements, address open challenges, and propose future research directions to improve the development and applicability of XAI in ubiquitous, pervasive, and wearable computing. Ultimately, the workshop seeks to enhance user trust, understanding, interaction, and adoption, ensuring that AI-driven solutions are not only more explainable but also better aligned with ethical standards and user expectations.
Ähnliche Arbeiten
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
2017 · 20.336 Zit.
Generative Adversarial Nets
2023 · 19.841 Zit.
Visualizing and Understanding Convolutional Networks
2014 · 15.241 Zit.
"Why Should I Trust You?"
2016 · 14.227 Zit.
On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)
2024 · 13.114 Zit.