基本信息
浏览量:12
职业迁徙
个人简介
Research overview
Interpretability
Currently I am working on the interpretability of machine learning algorithms. In a nutshell, state-of-the-art is achieved by quite complicated models such as deep neural networks, how can we understand why a particular decision is made by such a model? I am especially interested in providing theoretical guarantees for current interpretability methods. Recently, together with coauthors, we studied extensively LIME, arguably one of the most popular. The image below is from our latest paper and shows what happens with a linear model on an image from MNIST. See my publications page for more details, and feel free to reach out to me if you are interested in the topic!
Interpretability
Currently I am working on the interpretability of machine learning algorithms. In a nutshell, state-of-the-art is achieved by quite complicated models such as deep neural networks, how can we understand why a particular decision is made by such a model? I am especially interested in providing theoretical guarantees for current interpretability methods. Recently, together with coauthors, we studied extensively LIME, arguably one of the most popular. The image below is from our latest paper and shows what happens with a linear model on an image from MNIST. See my publications page for more details, and feel free to reach out to me if you are interested in the topic!
研究兴趣
论文共 29 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
CoRR (2023)
引用0浏览0EI引用
0
0
arxiv(2023)
引用0浏览0EI引用
0
0
Buntheng LY, Sonny Finsterbach, Marta Nuñez-García,Nicolas Cedilnik,Soumaya Sridi, Josquin Harrison,Pierre Jaı̈s,Damien Garreau,Hubert Cochet,Maxime Sermesant
Heart Rhythmno. 5 (2023): S121-S121
arxiv(2023)
引用0浏览0引用
0
0
arXiv (Cornell University) (2023)
引用0浏览0引用
0
0
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