Machine Learning Yearning
目 录
简介
NG的手稿，已出全。我这里边学习边翻译，随手记录之，加深学习印象，仅供学习交流。
更好阅读体验，移步gitbook：https://xiaqunfeng.gitbooks.io/machine-learning-yearning/content/
声明：本rep是自己学习过程的一个记录，仅用于学习目的。
更新记录：
- update 2018.04.25：NG终于出15~19章的手稿啦，等的好辛苦（DONE）
Tips：在原先的12章和13章之间新增一个章节
13 Build your first system quickly, then iterate，原先的chapter13变为14，chapter14变为15
- update 2018.05.02：手稿 20~22 章已出（DONE）
- update 2018.05.09：手稿 23~27 章已出（DONE）
- update 2018.05.16：手稿 28~30 章已出（DONE）
- update 2018.05.23：手稿 31~32 章已出（DONE）
- update 2018.05.30：手稿 33~35 章已出（DONE）
- update 2018.06.06：手稿 36~39 章已出（DONE）
- update 2018.06.13：手稿 40~43 章已出（DONE）
- update 2018.06.20：手稿 44~46 章已出（DONE）
- update 2018.06.27：手稿 47~49 章已出（DONE）
- update 2018.07.04：手稿 50~52 章已出（DONE）
- update 2018.09.29：手稿 53~58 章已出（DONE）
业余时间翻译，水平有限，如有不妥或错误之处，欢迎不吝赐教。
目的
这本书的目的是教你如何做组织一个机器学习项目所需的大量的决定。 你将学习：
如何建立你的开发和测试集
基本错误分析
如何使用偏差和方差来决定该做什么
学习曲线
将学习算法与人类水平的表现进行比较
调试推理算法
什么时候应该和不应该使用端到端的深度学习
按步进行错误分析
翻译章节
Chapter 1、Why Machine Learning Strategy
Chapter 2、How to use this book to help your team
Chapter 3、Prerequisites and Notation
Chapter 4、Scale drives machine learning progress
Setting up development and test sets
Chapter 5、Your development and test sets
Chapter 6、Your dev and test sets should come from the same distribution
Chapter 7、How large do the dev/test sets need to be?
Chapter 8、Establish a single-number evaluation metric for your team to optimize
Chapter 9、Optimizingandsatisficingmetrics
Chapter 10、Having a dev set and metric speeds up iterations
Chapter 11、When to change dev/test sets and metrics
Chapter 12、Takeaways: Setting up development and test sets
Basic Error Analysis
Chapter 13、Build your first system quickly, then iterate
Chapter 14、Error analysis: Look at dev set examples to evaluate ideas
Chapter 15、Evaluate multiple ideas in parallel during error analysis
Chapter 16、Cleaning up mislabeled dev and test set examples
Chapter 17、 If you have a large dev set, split it into two subsets, only one of which you look at
Chapter 18、How big should the Eyeball and Blackbox dev sets be?
Chapter 19、Takeaways: Basic error analysis
Bias and Variance
Chapter 20、Bias and Variance: The two big sources of error
Chapter 21、Examples of Bias and Variance
Chapter 22、Comparing to the optimal error rate
Chapter 23、Addressing Bias and Variance
Chapter 24、Bias vs. Variance tradeoff
Chapter 25、Techniques for reducing avoidable bias
Chapter 26、Error analysis on the training set
Chapter 27、Techniques for reducing variance
Learning curves
Chapter 28、Diagnosing bias and variance: Learning curves
Chapter 29、Plotting training error
Chapter 30、Interpreting learning curves: High bias
Chapter 31、Interpreting learning curves: Other cases
Chapter 32、Plotting learning curves
Comparing to human-level performance
Chapter 33、Why we compare to human-level performance
Chapter 34、How to define human-level performance
Chapter 35、Surpassing human-level performance
Training and testing on different distributions
Chapter 36、When you should train and test on different distributions
Chapter 37、How to decide whether to use all your data
Chapter 38、How to decide whether to include inconsistent data
Chapter 40、Generalizing from the training set to the dev set
Chapter 41、Identifying Bias, Variance, and Data Mismatch Errors
Chapter 42、Addressing data mismatch
Chapter 43、Artificial data synthesis
Debugging inference algorithms
Chapter 44、The Optimization Verification test
Chapter 45、General form of Optimization Verification test
Chapter 46、Reinforcement learning example
End-to-end deep learning
Chapter 47、The rise of end-to-end learning
Chapter 48、More end-to-end learning examples
Chapter 49、Pros and cons of end-to-end learning
Chapter 50、Choosing pipeline components: Data availability
Chapter 51、Choosing pipeline components: Task simplicity
Chapter 52、Directly learning rich outputs
Error analysis by parts
Chapter 53、 Error analysis by parts
Chapter 54、Attributing error to one part
Chapter 55、General case of error attribution
Chapter 56、Error analysis by parts and comparison to human-level performance
Chapter 57、Spotting a flawed ML pipeline
Conclusion
Chapter 58、Building a superhero team - Get your teammates to read this
英文原文
详见 draft 目录：
01-14章：Ng_MLY01-01-14.pdf
15-19章：Ng_MLY02-15-19.pdf
20-22章：Ng_MLY03-20-22.pdf
23-27章：Ng_MLY04-23-27.pdf
28-30章：Ng_MLY05-28-30.pdf
31-32章：Ng_MLY06-31-32.pdf
33-35章：Ng_MLY07-33-35.pdf
36-39章：Ng_MLY08-36-39.pdf
40-43章：Ng_MLY09-40-43.pdf
44-46章：NG_MLY10-44-46.pdf
47-49章：NG_MLY11-47-49.pdf
50-52章：Ng_MLY12-50-52.pdf
53-58章：Ng_MLY13-53-58.pdf