Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
（完结）Andrew NG Machine-Learning-Yearning translation documents（吴恩达《Machine Learning Yearning》中文翻译及英文原稿）
| Date | Stars |
|---|---|
| 2026-07-31 | 273 |
| 2026-08-02 | 273 |
| 2026-08-06 | 273 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Machine Learning Yearning 本项目是 Andrew NG 的关于机器学习策略的工具书的中文翻译稿源文件！（非商用翻译） *欢迎Star* 更好的阅读体验，请移步本人博客：[博客传送门](https://alberthg.github.io/tags/#maching%20learning%20yearning) 本书的英文原稿全文已于2018年9月29日全部推送完毕，感谢 Andrew NG。 官网传送门：[https://www.deeplearning.ai/](https://www.deeplearning.ai/) -OR- [http://www.mlyearning.org/](http://www.mlyearning.org/) 目的 ------- 根据NG的介绍，本书重点不是 ML 的算法，而是如何使 ML 算法发挥作用。琳琅满目的 ML 算法就像是工具箱里边的各种工具一样，这本书则是教会人们如何使用这些工具。 对于书名《Machine Learning Yearning》，我将其翻译为《机器学习要领》，希望能表达出 Andrew NG 编写这本书的目的: > focused not on teaching you ML algorithms, but on how to make ML algorithms work. 经验即要领，同时单词「yearning」读音和「要领」相似，故以此名之。 在原稿中，Andrew NG 把每一个主题都浓缩到 1-2 页的阅读量，是非常精炼的： - 1-4：绪论 「Introduction」； - 5-12：配置开发集和训练集 「Setting up development and test sets」； - 13-19：基本误差分析 「Basic Error Analysis」； - 20-27：偏差和方差 「Bias and Variance」； - 28-32：学习曲线 「Learning curves」； - 33-35：比较人类水平表现 「Comparing to human-level performance」； - 36-43：不同分布下的训练和测试 「Training and testing on different distributions」； - 44-46：调试推理算法 「Debugging inference algorithms」； - 47-52：端到端的深度学习 「End-to-end deep learning」； - 53-57：根据组件执行误差分析 「Error analysis by parts」； - 58：全书结语「Conclusion」。 翻译的水平有限（如有错误，请指出），而且有些地方是在经过自己的理解之后并尽量遵照原文进行翻译，只是希望尽可能的读起来通顺。 翻译稿 ------- 在本书中，你将学习多达 50 多个 Andrew NG 多年总结的工程要领： ### 绪论 「Introduction」 [1、为什么需要机器学习策略](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter1.md) [2、如何利用本书帮助你的团队](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter2.md) [3、预备知识和符号约定](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter3.md) [4、规模化驱动下的机器学习发展](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter4.md) ### 配置开发集和训练集 「Setting up development and test sets」 随着机器学习正朝着更大的数据集方向发展，关于配置开发/测试集的准则也在发生变化，本章内容将指导你如何在团队中调整机器学习策略，以及如何设置开发集和测试集，以适应现代化的机器学习项目。 [5、你的开发集和测试集](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter5.md) [6、发集和测试集应当服从同一分布](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter6.md) [7、开发集/测试集多大合适](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter7.md) [8、为团队进行算法优化建立单一数字评估指标](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter8.md) [9、优化和满足指标](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter9.md) [10、使用开发集和评估指标加速迭代](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter10.md) [11、何时更改开发/训练集和评估指标](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter11.md) [12、小结：设置开发和测试集](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter12.md) ### 基本误差分析 「Basic Error Analysis」 本章内容将通过描述手动分析误差的流程，来为项目优化选择合适的方向。 [13、快速搭建第一个系统并开始迭代](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter13.md) [14、误差分析：查看开发集样本来评估想法](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter14.md) [15、在误差分析中并行评估多个想法](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter15.md) [16、清除标注错误的开发/测试集数据](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter16.md) [17、 如果你有一个很大的开发集，拆分为两半，并只关注其中一个](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter17.md) [18、眼球开发集和黑盒开发集应该多大](https://github.com/AlbertHG/Machine-Learning-Yearning-Chinese-ver/blob/master/mlyearning-Chinese%20ver/chapter18.md) [19、小结：基本误差分
Excerpt of 11,149 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:0d3084404afe2ff6, llm:Repository description and README: Chinese translation of Andrew Ng's 'Machine Learning Yearning' (topics: machine-learning-yearning, translation, chinese).
matched fp:0d3084404afe2ff6, llm:Repository description and README: Chinese translation of Andrew Ng's 'Machine Learning Yearning' (topics: machine-learning-yearning, translation, chinese).