ML Books Machine Learning (non-DL)

ML Books Machine Learning (non-DL)

2018-07-07. Category & Tags: Machine Learning, Artificial Intelligence, Book

See also:

Favoured #

  • DSML (Kroese, Botev et.al. - Chapman Press 2019-11) 《Data Science and Machine Learning: Mathematical and Statistical Methods》. With public datasets, code and pdf online. ISBN 9781138492530.

    • 官方英文PDF
    • 中文版：(澳) 迪尔克·P. 克洛泽 等 著，Dirk P. Kroese，于俊伟, 刘楠 (译)，《数据科学与机器学习: 数学与统计方法》，机械工业出版社, ISBN 9787111711391, 2023 image.png

  • NNDL, Neural Networks and Deep Learning. (Michael Nielsen 2016)

    • Keywords: Gradient Descend, Batch,CNN, RNN, Attention, Gaussian Mix., RBM, DBN, GAN, RL, TF, PyTorch: equation, pseudocode 伪码, exercise … 等等，大量基本概念和基础知识。 公开了所有代码等内容的（中文）电子书。
    • PDF, PPT, code, exercise & solution, etc., python3 复现 (old: py2).
    • 中文版：
    • 早期志愿翻译版：邱锡鹏（译） 2020.06；更早：Xiaohu Zhu 和 Freeman Zhang, 2016.
    •  ![image.png](https://jsd.cdn.zzko.cn/gh/ol-storage/picx-images-hosting@master/2026/20260314230226905.png).
    • 近似同名书：Charu C. Aggarwal，《Neural Networks and Deep Learning: A Textbook》, 从目录看来，内容也非常相似。
      • Springer，1st. Ed. ISBN 9783319944630, 2018
      • Springer，2nd. Ed. ISBN 9783031296413，2023-06-30
      • image.pngimage.png.
      • 中文版：[美] 查鲁·C. 阿加沃尔，《神经网络与深度学习》，机械工业出版社, ISBN 9787111686859，2021-08
      • image.png.

  • MLAPP (Kevin Murphy), Machine Learning - A Probablistic Perspective, is more comprehensive, insightful and interesting, and contains more “real” examples/problems. However, the presents are kinda out of order, which can be difficult to follow for a first book.

    • image.png.

  • PRML (Christopher Bishop, 微软剑桥研究院实验室主任), Pattern Recognition and Machine Learning, is for the ones are very comfortable with calculus/linear algebra, Bayes-oriented, advanced 要求数学（高数、线代）较好。

  • ESL (Trevor Hastie), Elements of Statistical Learning, 2n ed. Springer 2017. Contains even harder math (ref: zhihu ans. –> point.2), stats.-oriented, advanced. (中文翻译《统计学习要素》、R 代码实现及其习题解答 via Python 数据科学)

Good Text Books (for Master & PhD ?) #

  • Machine Learning by Peter Flach (Cambridge University Press 2012) - The Art and Science of Algorithms that Make Sense of Data. [The examples in this book are clear and easy to understand, with pseudocode 伪码.]
    • 中文版：彼得·弗拉赫，段菲 (译)，机器学习，人民邮电出版社，ISBN 9787115405777，2015-12 / 2016-01-01
    • image.png
  • Machine Learning by Tom M Mitchell (McGraw-Hill 1997). (Classical, many original terms and ideas.)
  • PRML
    • (For details, see “favoured” above)
    • image.png
  • 南京大学 周志华《机器学习》 (" 西瓜书 “) 清华大学出版社 2016：有伪码，但是比 Peter Flach 的难懂，需要较为熟悉统计学，旁注格式不如他的另一本书《集成学习》中的 in-line 注释，但是对于博士或者数学不错的硕士是入门的书籍，书中的例子十分形象且简单易懂。 类似清华的红皮 PR，没有推导过程，推导可以参考开源南瓜书：西瓜书的公式推导 (“南瓜书 The Pumpkin Book”), by 周志华学生(据说)。
    • image.png image.png.
  • MLY (Andrew Ng), Machine Learning Yearning (EN full: ch1-13), 《CN: 机器学习秘籍》(技巧)(CN Web online), (CN Github) and someone’s notes: part 1 (bak), part 2 (bak) and part 3.
    • .

More Codes #

More Books #

Dated #

  • Programming Collective Intelligence 《集体智慧编程》 2007 O’REILLY by Toby Segaran: Programming selected algorithms from scratch. Good to read when learning some ML courses (e.g. ML by Andrew Ng, Stanford).

Ref: