How does machine learning work? Systematically, of course. Don’t have time for that? Use fragmented time to learn! Many people commute two hours a day and spend a lot of time looking at their phones. So I put some basic knowledge of machine learning into an online machine learning manual, just open the wechat collection can learn! It’s like memorizing TOEFL words. (Author: Huang Haiguang [1])

The machine learning manual is divided into three parts: mathematical fundamentals, classical machine learning algorithms and statistical learning methods. If you have time, you can learn these three parts in sequence. If you have less time, I suggest you directly read the classical machine learning algorithm and check the basic mathematics when you have a problem. You can also read the classical machine learning algorithm and the statistical learning method at the same time to check and fill in the gaps.

Machine learning Manual

1. Mathematical foundation

1. Advanced Mathematics

I would like to recommend my math notes when I took the postgraduate entrance examination and the postgraduate entrance examination. I extracted the part of machine learning and almost covered all the advanced mathematics formulas required by machine learning: I made the online reading version.

**** Click to open the university advanced mathematics essence

2. The theory of probability

  • The preferred

    I recommend the probability theory part of the basic materials for the Machine learning course CS229 at Stanford University. This is the basic materials for various Stanford artificial intelligence courses, which are optimized for machine learning. It can be said that it is a classic material. (Original file download [2])

**** Click here to open a translation of CS229 Probability Theory

  • alternative

    I would like to recommend my math notes when I took the postgraduate and doctoral entrance exams. I extracted the part of machine learning and almost covered all linear algebra formulas required by machine learning:

**** Click to open the university probability theory essence ****

3. Linear algebra

  • The preferred

    I recommend the linear algebra section of the basic materials of Stanford UNIVERSITY CS229 machine learning course, which is the basic materials of various Stanford artificial intelligence courses. It is optimized for machine learning and can be said to be a classic material. (Original file download [3])

**** Click to open the translation of CS229 linear algebra

  • alternative

    I would like to recommend my math notes when I took the postgraduate and doctoral entrance exams. I extracted the part of machine learning and almost covered all linear algebra formulas required by machine learning:

**** Click to open college linear Algebra highlights

Making:

Github.com/fengdu78/Da…

Classical machine learning algorithms

The classical algorithm of machine learning is mainly the selected part of Ng’s machine learning course [4], and the decision tree part is added. How to master the classical algorithm of machine learning in the shortest time? I recommend to learn the essence of the algorithm, so that the learning progress will be a little faster.

(Click on the catalog to read online)

Part ONE: Regression

Part two: Logistic regression

Part three: Support vector machines

Part FOUR: Unsupervised learning

Part FIVE: Anomaly detection and recommendation system

Part six: Decision trees

  • The first paper: Base tree (including ID3, C4.5, CART)
  • Article 2: Random Forest, Adaboost, GBDT
  • Article 3: Xgboost and LightGBM

Making:

Github.com/fengdu78/Co…

Iii. Statistical Learning Methods

The first edition of Statistical Learning Methods [5] by Professor Li Hang was published in 2012, which describes statistical machine learning methods, mainly some commonly used supervised learning methods. The first edition is identical to the first twelve chapters of the second edition, with more unsupervised learning (twelve more chapters later than the first edition), thus covering the main content of traditional statistical machine learning methods. (Click on the catalog to read online)

directory

Chapter 1 introduction to statistical learning and supervised learning

Chapter 2 perceptron

Chapter 3 k nearest neighbor method

Chapter 4 naive Bayes method

Chapter 5 decision tree

Chapter 6: Logistic Logistic Regression and maximum entropy model

Chapter 7 Support vector machines

Chapter 8 Methods of promotion

Chapter 9 EM algorithm and its extension

Chapter 10 Hidden Markov model

Chapter 11 conditional random airport

Chapter 12 summarizes the methods of supervised learning

Making: github.com/fengdu78/li…

conclusion

In this paper, the essence of machine learning has been made into a manual, which can be learned by opening wechat. It is suitable for friends who have little time to learn machine learning. They can study on their mobile phones when commuting.

The resources

[1] Huang Haiguang: github.com/fengdu78 [2] probability original file download: http://cs229.stanford.edu/summer2019/cs229-prob.pdf [3] linear algebra original file download: Cs229.stanford.edu/summer2019/… [4] machine learning courses: https://www.coursera.org/course/ml [5] the statistical learning methods: baike.baidu.com/item/ statistical learning method…

Machine Learning Online Manual Deep Learning online Manual AI Basics download (PDF updated to25Set) site QQ group1003271085To join the wechat group, please reply to "add group" to get a discount station knowledge planet coupon, please reply to "knowledge planet" like the article, click on itCopy the code