本内容是Andrew NG的 My Machine Learning Yearning 1-22章内容的翻译及其原稿.
亲爱的朋友,你是如何组织一个人工智能(AI)项目的呢?
人工智能(AI),机器学习(Machine Leaning)和深度学习(Deep learning)正在改变众多行业。我一直在写此书——Machine Learning Yearning,来教你如何构建机器学习项目。
本书的重点不在于教授机器学习算法,而在于使机器学习算法发挥作用。一些人工智能技术会给你一个锤子,而本书教你如何使用锤子。如果你渴望成为人工智能技术的领导者并想学习如何为你的团队设定方向,这本书将会有所帮助。
阅读完Machine Learning Yearning之后,你将能够:
- 为人工智能项目最有前途的方向设立优先级
- 诊断机器学习系统中的错误
- 在复杂设置中构建机器学习,例如不匹配的训练集/测试集
- 建立一个可以人类比较或超越人类表现的机器学习项目
- 了解何时以及如何应用端到端学习(end-to-end learning),迁移学习(transfer learning)和多任务学习(multi-task learning)
从历史上看,学习如何制定这些“策略”决策的唯一方法是在研究生课程或公司中做多年的学徒。我正在写的Machine Learning Yearning可以帮你快速的获得这项技能,以便你可以更好地构建人工智能系统。
本书大约100页,包含很多易于阅读的1-2页的章节。如果你希望收到每章完成后的草稿,请注册邮件列表。
—— 吴恩达(Andrew Ng)
gitbook阅读体验更好,欢迎来点击下面链接阅读翻译版:
https://yuchenchen.gitbook.io/machine-learning-yearning/
https://github.com/yucc2018/machine-learning-yearning
17. 如果你有一个很大的开发集,将它分成两个,而且你只看一个
20. 偏差(Bias)和方差(Variance):错误的两大来源
- Addressing Bias and Variance
- Bias vs. Variance tradeoff
- Techniques for reducing avoidable bias
- Techniques for reducing Variance
- Error analysis on the training set
- Diagnosing bias and variance: Learning curves
- Plotting training error
- Interpreting learning curves: High bias
- Interpreting learning curves: Other cases
- Plotting learning curves
- Why we compare to human-level performance
- How to define human-level performance
- Surpassing human-level performance
- Why train and test on different distributions
- Whether to use all your data
- Whether to include inconsistent data
- Weighting data
- Generalizing from the training set to the dev set
- Addressing Bias, and Variance, and Data Mismatch
- Addressing data mismatch
- Artificial data synthesis
- The Optimization Verification test
- General form of Optimization Verification test
- Reinforcement learning example
- The rise of end-to-end learning
- More end-to-end learning examples
- Pros and cons of end-to-end learning
- Learned sub-components
- Directly learning rich outputs
- Error Analysis by Parts
- Beyond supervised learning: What’s next?
- Building a superhero team - Get your teammates to read this
- Big picture
- Credits
原文原版手稿已经更新到19章,下载链接分别如下:
我自己手动将上面两部分合并,成为1-19章的合集。想下载一个的直接点下面这个链接。