公平性:程式設計練習
透過集合功能整理內容
你可以依據偏好儲存及分類內容。
以下練習示範如何在
以及如何使用偏誤補救策略因應公平性
問題:
程式設計練習直接在瀏覽器中執行 (無需設定
必要!) 使用 Colaboratory 程式碼
平台。Colaboratory 支援大多數主要瀏覽器,
徹底測試了 Chrome 和 Firefox 電腦版。
除非另有註明,否則本頁面中的內容是採用創用 CC 姓名標示 4.0 授權,程式碼範例則為阿帕契 2.0 授權。詳情請參閱《Google Developers 網站政策》。Java 是 Oracle 和/或其關聯企業的註冊商標。
上次更新時間:2024-08-13 (世界標準時間)。
[null,null,["上次更新時間:2024-08-13 (世界標準時間)。"],[[["\u003cp\u003eThis exercise demonstrates how to audit data sets for fairness and apply bias-remediation strategies.\u003c/p\u003e\n"],["\u003cp\u003eThe programming exercises are run directly in your browser using the Colaboratory platform with no setup required.\u003c/p\u003e\n"],["\u003cp\u003eColaboratory is supported on most major browsers and is most thoroughly tested on desktop versions of Chrome and Firefox.\u003c/p\u003e\n"],["\u003cp\u003eUsers can access a Help Center for support with machine learning education.\u003c/p\u003e\n"]]],[],null,["# Fairness: Programming exercise\n\nThe following exercise demonstrates how to audit data sets with fairness in\nmind, and how to employ bias-remediation strategies to address fairness\nissues: \n[Open fairness exercise](https://colab.research.google.com/github/google/eng-edu/blob/main/ml/cc/exercises/fairness_income.ipynb?utm_source=mlcc&utm_campaign=colab-external&utm_medium=referral&utm_content=fairness)\n\nProgramming exercises run directly in your browser (no setup\nrequired!) using the [Colaboratory](https://colab.research.google.com)\nplatform. Colaboratory is supported on most major browsers, and is most\nthoroughly tested on desktop versions of Chrome and Firefox. \n[Help Center](https://support.google.com/machinelearningeducation)"]]