基本信息
浏览量:0
职业迁徙
个人简介
With the ever-growing influence of machine learning in our lives, there is an increasing demand of interpretability for the AI systems. The demand is highlighted when we tackle safety-critical applications, the ones which accompany privacy and security concerns, or the ones that could benefit from auditing by domain experts. With interpretability, comes human understandability, the ease of formal reasoning, and a more direct control on the properties of the system. I aim to study the problem of interpretability in machine learning via combinatorial optimization and to explore the huge potential with regards to the influence of formal languages and automata on adding clarity to the commonly black-box models of machine learning.
研究兴趣
论文共 5 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
Constraintsno. 2 (2023): 166-202
CPpp.33:1-33:19, (2023)
引用0浏览0EI引用
0
0
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