机器学习入门书籍推荐

Hands On Machine Learning with Scikit Learn and TensorFlow，也就是下面这本。
　　
　　作为一个半路出家的小菜鸡，为了较系统学习机器学习，看过好几本相关书籍，除了上面说的这一本，还看过周志华的《机器学习》、李航的《统计学习方法》、Ian Goodfellow《Deep Learning》。最后看的《Hands On ML》，每本书都感觉相见恨晚，但是《Hands On ML》尤甚。
【优点】
　　这四本书每本都看了至少两遍吧，所以还是至少有个宏观的了解，个人觉得新手入门最合适的还是《Hands On ML》，原因如下（对英文版而言）：
　　（1）原理易懂：
　　　　　　个人觉得，虽然读的是英文版，对于原理的解释比很多中文版的资料更好懂。
　　（2）更贴近实操：
　　　　　　书中代码例子很多，真的是手把手教你。而且github上有很全面的代码和解释。
　　（3）内容比较全面：
　　　　　　包括经典的机器学习，到深度学习，还有最后一章的强化学习（算是介绍吧）。
【不足】
　　既然作为初学者入门的书，也有其不足，本书最大的不足就是——公式太少，意思就是理论细节不太够。所以初学者吃透了这本书，就可以考虑更有深度的书籍，例如其他三本（不过有不少重复的地方）。
【作者的话】
　　下面附上原书作者的在书后的后记和致谢，其言辞恳恳，读了颇有感动，真是我辈良师：
——————————————————————————————————————
Thank You!
Before we close the last chapter of this book, I would like to thank you for reading it
up to the last paragraph. I truly hope that you had as much pleasure reading this book
as I had writing it, and that it will be useful for your projects, big or small.
If you find errors, please send feedback. More generally, I would love to know what
you think, so please don’t hesitate to contact me via O’Reilly, or through the ageron/
handson-ml GitHub project.
Going forward, my best advice to you is to practice and practice: try going through all
the exercises if you have not done so already, play with the Jupyter notebooks, join
Kaggle.com or some other ML community, watch ML courses, read papers, attend
conferences, meet experts. You may also want to study some topics that we did not
cover in this book, including recommender systems, clustering algorithms, anomaly
detection algorithms, and genetic algorithms.
My greatest hope is that this book will inspire you to build a wonderful ML applica‐
tion that will benefit all of us! What will it be?

Aurélien Géron, November 26th, 2016
——————————————————————————————————————