.png){kind=icon}
返回
Toward eXplainabile Data-Driven Control (XDDC): The Property-Preserving Framework
.png){kind=icon}
OA
AI
DOI：10.1109/LCSYS.2024.3395181.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As Artificial Intelligence (AI) techniques continue to advance, the need for explainability becomes increasingly crucial, especially in sensitive or safety-critical domains. eXplainable AI (XAI) has emerged to address this need, aiming to enhance transparency in complex models. While XAI has gained traction in mainstream machine learning, its application in data-driven control systems remains relatively unexplored. This letter introduces a novel concept of explainability tailored for data-driven control, allowing one to design feedback loops from data incorporating prior knowledge and preserving important system properties. Through two case studies, we demonstrate the efficacy of this property-preserving framework in direct and indirect data-driven control system design. This letter lays the foundation for further research at the intersection of AI and data-driven control, offering insights into enhancing transparency in complex control systems.
Keyword:
Batteries
Mathematical models
Explainable AI
Training
Data models
Hybrid power systems
Closed box
Data driven control
machine learning
identification for control
期刊
I
IF:
2
论文数:
94
被引数:
5.0K
机构
引用论文
Intercellular Adhesion Molecule 1 (ICAM-1) Gene Variant is Associated with Coronary Artery Calcification Independent of Soluble ICAM-1 Levels细胞间粘附分子1 (ICAM-1) 基因变异与冠状动脉钙化相关，与可溶性ICAM-1水平无关
PREAI
分享收藏Identification and cloning of unc-119, a gene expressed in the Caenorhabditis elegans nervous system..png)
GeneticsOAAI
GeneticsIF0
OAAI分享收藏
查看更多内容