On Formalizing Fairness in Prediction with Machine Learning
公平的定义和衡量标准 文献中提出了几种公平的定义，但还没有形成明确的共识。然而，这些定义可以用作在ML测试中检测违反公平性的预言。 为了帮助说明ML公平性的形式化，我们使用X表示一组个体，Y表示在对X中的每个个体进行决策时的真实标签集。设h是训练好的机器学习预测模型。设A为敏感属性集，Z为剩余属性。 1)Fairness Through Unawareness 无意识公平。无意识公平(FT
相关文章
- 1. hand on machine learning with
- 2. [GPU] Machine Learning on C++
- 3. Chapter 9 On-policy Prediction with Approximation
- 4. 【机器学习中的公平性】Fairness in Machine Learning
- 5. Tackling Climate Change with Machine Learning
- 6. Machine and Deep Learning with Python
- 7. An Introduction to Machine Learning with Python
- 8. Fixed error when submitting assignments in Machine Learning on Coursera
- 9. 论文解读：Multimodal Machine Translation with Embedding Prediction
- 10. Classification and inference with machine learning
- 更多相关文章...
- • Docker Machine - Docker教程
- • SQL IN 操作符 - SQL 教程
- • Java Agent入门实战（一）-Instrumentation介绍与使用
- • Java Agent入门实战（三）-JVM Attach原理与使用
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. hand on machine learning with
- 2. [GPU] Machine Learning on C++
- 3. Chapter 9 On-policy Prediction with Approximation
- 4. 【机器学习中的公平性】Fairness in Machine Learning
- 5. Tackling Climate Change with Machine Learning
- 6. Machine and Deep Learning with Python
- 7. An Introduction to Machine Learning with Python
- 8. Fixed error when submitting assignments in Machine Learning on Coursera
- 9. 论文解读：Multimodal Machine Translation with Embedding Prediction
- 10. Classification and inference with machine learning