期刊
SCIENCE
卷 366, 期 6468, 页码 999-+出版社
AMER ASSOC ADVANCEMENT SCIENCE
DOI: 10.1126/science.aag3311
关键词
-
资金
- NSF CAREER [1350984, 1453474]
- NSF [1763423]
- Institute of Educational Science [R305A130215]
- Direct For Computer & Info Scie & Enginr
- Division of Computing and Communication Foundations [1453474] Funding Source: National Science Foundation
- Division of Computing and Communication Foundations
- Direct For Computer & Info Scie & Enginr [1763423] Funding Source: National Science Foundation
- Div Of Information & Intelligent Systems
- Direct For Computer & Info Scie & Enginr [1350984] Funding Source: National Science Foundation
Intelligent machines using machine learning algorithms are ubiquitous, ranging from simple data analysis and pattern recognition tools to complex systems that achieve superhuman performance on various tasks. Ensuring that they do not exhibit undesirable behavior-that they do not, for example, cause harm to humans-is therefore a pressing problem. We propose a general and flexible framework for designing machine learning algorithms. This framework simplifies the problem of specifying and regulating undesirable behavior. To show the viability of this framework, we used it to create machine learning algorithms that precluded the dangerous behavior caused by standard machine learning algorithms in our experiments. Our framework for designing machine learning algorithms simplifies the safe and responsible application of machine learning.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据