CSET2024AI安全的关键概念机器学习中可靠的不确定性量化方法分析报告英文版13页

Issue BriefJune 2024Key Concepts in AI SafetyReliable Uncertainty Quantification in Machine LearningAuthors Tim G. J. Rudner Helen Toner Center for Security and Emerging Technology | 1 This paper is the fifth installment in a series on “AI safety,” an area of machine learning research that aims to identify causes of unintended behavior in machine learning systems and develop tools to ensure these systems work safely and reliably. Other papers in the series describe three categories of AI safety issues—problems of robustness, assurance, and specification. This paper introduces the idea of uncertainty quantification, i.e., training machine learning systems that “know what they don’t know.” Introduction The last decade of progress in machine learning research has given rise to systems that are surprisingly capable but also notoriously unreliable. The chatbot ChatGPT, developed by OpenAI, provides a good illustration of this tension. Users interacting with the system after its release in