摘要
透過集合功能整理內容
你可以依據偏好儲存及分類內容。
從機器學習的角度界定問題分為兩個步驟：
請執行下列操作，確認 ML 是合適的做法：
請按照下列步驟，以機器學習術語定義問題：
- 定義理想結果和模型目標。
- 找出模型的輸出內容。
- 定義成功指標。
這些步驟有助於設定明確目標，並提供與其他機器學習專業人員合作的共用架構，進而節省時間和資源。
請完成下列練習，架構機器學習問題並擬定解決方案：
負責任的 AI 技術
導入機器學習解決方案時，請務必遵守 Google 的負責任的 AI 技術原則。
如要實際瞭解如何改善機器學習的公平性及減少偏誤，請參閱 MLCC 公平性模組。
持續掌握情況
更多機器學習學習資源
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：2025-08-04 (世界標準時間)。
[null,null,["上次更新時間：2025-08-04 (世界標準時間)。"],[[["\u003cp\u003eFraming a Machine Learning (ML) problem involves understanding the problem, identifying a use case, understanding the data, and then defining the desired outcome, model output, and success metrics.\u003c/p\u003e\n"],["\u003cp\u003eThese steps help in setting clear objectives and establishing a collaborative framework when working with other ML professionals.\u003c/p\u003e\n"],["\u003cp\u003eApplying ML can raise privacy and ethical issues which need careful consideration before deploying a model, using available resources to mitigate these risks.\u003c/p\u003e\n"],["\u003cp\u003eFurther learning resources are available on data preparation, feature engineering, testing, debugging in ML, and responsible AI practices.\u003c/p\u003e\n"]]],[],null,["# Summary\n\n\u003cbr /\u003e\n\nFraming a problem in terms of ML is a two-step process:\n\n1. Verify that ML is a good approach by doing the following:\n\n - Understand the problem.\n - Identify a clear use case.\n - Understand the data.\n2. Frame the problem in ML terms by doing the following:\n\n - Define the ideal outcome and the model's goal.\n - Identify the model's output.\n - Define success metrics.\n\nThese steps can save time and resources by setting clear goals and providing a\nshared framework for working with other ML practitioners.\n\nUse the following exercises to frame an ML problem and formulate a solution:\n\n- [Framing an ML problem](/machine-learning/problem-framing/try-it/framing-exercise)\n- [Formulating a solution](/machine-learning/problem-framing/try-it/formulate-exercise)\n\nResponsible AI\n--------------\n\nWhen implementing ML solutions, always follow\n[Google's Responsible AI Principles](https://ai.google/responsibility/principles).\n\nFor a hands-on introduction for improving fairness and mitigating bias in\nML, see the [MLCC Fairness module](https://developers.google.com/machine-learning/crash-course/fairness).\n\nKeep learning\n-------------\n\n### More ML learning resources\n\n- [Data Preparation and Feature Engineering](/machine-learning/data-prep)\n- [Testing and Debugging in Machine Learning](/machine-learning/testing-debugging)\n- [People + AI Research](https://pair.withgoogle.com/)"]]
