.png){kind=icon}
返回
Risk-aware classification via uncertainty quantification
.png){kind=icon}
OA
AI
DOI：10.1016/j.eswa.2024.125906.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Autonomous and semi-autonomous systems are using deep learning models to improve decision-making. However, deep classifiers can be overly confident in their incorrect predictions, a major issue especially in safety-critical domains. The present study introduces three foundational desiderata for developing real- world risk-aware classification systems. Expanding upon the previously proposed Evidential Deep Learning (EDL), we demonstrate the unity between these principles and EDL's operational attributes. We then augment EDL empowering autonomous agents to exercise discretion during structured decision-making when uncertainty and risks are inherent. We rigorously examine empirical scenarios to substantiate these theoretical innovations. In contrast to existing risk-aware classifiers, our proposed methodologies consistently exhibit superior performance, underscoring their transformative potential in risk-conscious classification strategies.
Keyword:
Deep learning
Uncertainty quantification
Risk awareness
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.5
论文数:
2.9W
被引数:
10.2W
机构
引用论文
Phytochemical, nutritional and antioxidant capacity of five Ivorian edible leaves aqueous extracts
OAAI
OAAI分享收藏分享收藏Uncertainty estimation for stereo matching based on evidential deep learning基于证据深度学习的立体匹配不确定性估计.png)
PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏A review of uncertainty quantification in deep learning: Techniques, applications and challenges深度学习中的不确定性量化: 技术、应用与挑战INFORMATION FUSIONOAAI
INFORMATION FUSIONIF15.5
OAAI分享收藏Evidential Deep Learning for Guided Molecular Property Prediction and Discovery用于引导分子特性预测和发现的证据深度学习ACS CENTRAL SCIENCEOAAI
ACS CENTRAL SCIENCEIF10.4
OAAI分享收藏UncertaintyFuseNet: Robust uncertainty-aware hierarchical feature fusion model with Ensemble Monte Carlo Dropout for COVID-19 detectionINFORMATION FUSIONOAAI
INFORMATION FUSIONIF15.5
OAAI分享收藏
查看更多内容