Callisto: Entropy based test generation and data quality assessment for Machine Learning Systems
Callisto: Entropy based test generation and data quality assessment for Machine Learning Systems abstract。
解决的问题
机器学习系统越来越对地被应用,因此急切需要对基于机器学习的模型进行验证。
Abstract
因此本文提出了 Callisto
,一个用于生成测试用例和数据质量评估的框架。
其中,数据质量评估为数据中误标签识别。
收获与总结
- 数据质量评估中包括误标签识别
Jiangwen Sun, Feng-ying Zhao, Chong-Jun Wang, and Shifu Chen. Identifying and correcting mislabeled training instances. In Future Generation Communication and Networking, FGCN 2007, Ramada Plaza Jeju, Jeju-Island, Korea, December 6-8, 2007, Proceedings, pages 244– 250, 2007. URL: https://doi.org/10.1109/FGCN.2007.146, doi:10. 1109/FGCN.2007.146.
All articles in this blog are licensed under CC BY-NC-SA 4.0 unless stating additionally.