Robotics & Machine Learning Daily News2024,Issue(Jan.17) :1-1.

University of Mons Researcher Yields New Data on Artificial Intelligence (Explainability and Evaluation of Vision Transformers: An In-Depth Experimental Study)

Robotics & Machine Learning Daily News2024,Issue(Jan.17) :1-1.

University of Mons Researcher Yields New Data on Artificial Intelligence (Explainability and Evaluation of Vision Transformers: An In-Depth Experimental Study)

扫码查看

Abstract

By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Investigators discuss new findings in artificial intelligence. According to news reportingoriginating from Mons, Belgium, by NewsRx correspondents, research stated, “In the era of artificialintelligence (AI), the deployment of intelligent systems for autonomous decision making has surged acrossdiverse fields.”Funders for this research include Walloon Skywin Pole of Belgium.Our news reporters obtained a quote from the research from University of Mons: “However, thewidespread adoption of AI technology is hindered by the risks associated with ceding control to autonomoussystems, particularly in critical domains. Explainable artificial intelligence (XAI) has emerged as a criticalsubdomain fostering human understanding and trust. It addresses the opacity of complex models such asvision transformers (ViTs), which have gained prominence lately. With the expanding landscape of XAImethods, selecting the most effective method remains an open question, due to the lack of a ground-truthlabel for explainability. To avoid subjective human judgment, numerous metrics have been developed, witheach aiming to fulfill certain properties required for a valid explanation. This study conducts a detailedevaluation of various XAI methods applied to the ViT architecture, thereby exploring metrics criteria likefaithfulness, coherence, robustness, and complexity.”

Key words

University of Mons/Mons/Belgium/Europe/Artificial Intelligence/Emerging Technologies/Machine Learning

引用本文复制引用

出版年

2024
Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
段落导航相关论文