基本信息
浏览量:17
职业迁徙
个人简介
My research concentrates on finding ways to identify when a model is acting unfairly, curtailing this behavior when possible, and demonstrating that in some situations it is not possible. This research can take different shapes: it often concerns transparency and explainability in AI, since in order to understand how a model is unfair, we need to understand how it works in the first place. It also can consist of bringing attention to unexplored ways in which models can behave unfairly--for example, ways in which model instability can lead to unfairness. I also work on more practical methods of identifying discrimination, such as developing auditing techniques for machine learning models. Finally, I am also interested in connecting my theoretical work with practices surrounding the use machine learning systems.
研究兴趣
论文共 13 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
Social Science Research Network (2023)
引用0浏览0引用
0
0
PROCEEDINGS OF 2023 ACM CONFERENCE ON EQUITY AND ACCESS IN ALGORITHMS, MECHANISMS, AND OPTIMIZATION, EAAMO 2023 (2023): 36:1-36:11
SSRN Electronic Journalpp.850-863, (2022)
ACM Conference on Fairness, Accountability and Transparency (FAccT)pp.1479-1503, (2022)
Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency (2020)
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn