负责任地评估机器学习 (ML) 模型不仅仅需要计算总体损失指标。在将模型投入生产环境之前，请务必审核训练数据并评估预测是否存在偏差。
本单元将介绍可能会在训练数据中显现出来的不同类型的人为偏差。然后，该文档提供了识别和减少偏见的策略，并以公平性为考量因素评估模型性能。
公平性
如未另行说明，那么本页面中的内容已根据知识共享署名 4.0 许可获得了许可，并且代码示例已根据 Apache 2.0 许可获得了许可。有关详情，请参阅 Google 开发者网站政策。Java 是 Oracle 和/或其关联公司的注册商标。
最后更新时间 (UTC)：2025-07-27。
[null,null,["最后更新时间 (UTC)：2025-07-27。"],[[["\u003cp\u003eThis module focuses on identifying and mitigating human biases that can negatively impact machine learning models.\u003c/p\u003e\n"],["\u003cp\u003eYou'll learn how to proactively examine data for potential bias before model training and how to evaluate your model's predictions for fairness.\u003c/p\u003e\n"],["\u003cp\u003eThe module explores various types of human biases that can unintentionally be replicated by machine learning algorithms, emphasizing responsible AI development.\u003c/p\u003e\n"],["\u003cp\u003eIt builds upon foundational machine learning knowledge, including linear and logistic regression, classification, and handling numerical and categorical data.\u003c/p\u003e\n"]]],[],null,["# Fairness\n\n| **Estimated module length:** 110 minutes\n\nEvaluating a machine learning model (ML) responsibly requires doing more than\njust calculating overall loss metrics. Before putting a model into production,\nit's critical to audit training data and evaluate predictions for\n[bias](/machine-learning/glossary#bias-ethicsfairness).\n\nThis module looks at different types of human biases that can manifest in\ntraining data. It then provides strategies to identify and mitigate them,\nand then evaluate model performance with fairness in mind.\n| **Learning objectives**\n|\n| - Become aware of common human biases that can inadvertently be reproduced by ML algorithms.\n| - Proactively explore data to identify sources of bias before training a model.\n| - Evaluate model predictions for bias.\n| **Prerequisites:**\n|\n| This module assumes you are familiar with the concepts covered in the\n| following modules:\n|\n| - [Introduction to Machine Learning](/machine-learning/intro-to-ml)\n| - [Linear regression](/machine-learning/crash-course/linear-regression)\n| - [Logistic regression](/machine-learning/crash-course/logistic-regression)\n| - [Classification](/machine-learning/crash-course/classification)\n| - [Working with numerical data](/machine-learning/crash-course/numerical-data)\n| - [Working with categorical data](/machine-learning/crash-course/categorical-data)\n- [Datasets, generalization, and overfitting](/machine-learning/crash-course/overfitting) \n| **Key terms:**\n|\n| - [Bias (ethics/fairness)](/machine-learning/glossary#bias-ethicsfairness)\n- [Model](/machine-learning/glossary#model) \n[Help Center](https://support.google.com/machinelearningeducation)"]]