Open source address

Github.com/datawhalech…

【 introduction 】Learning materials on machine learning, ranging from classic books to free open courses to open source projects, are a huge convenience for learners. But online learning materials everywhere are mostly English materials, which can be stumped by poor English learners, do not know the words, understanding is not in place. Xiaobian can not help but ask: there is really no way. In fact, there are some good learning materials in Chinese, such as Zhou Zhihua’s watermelon book, Li Hang’s statistical learning methods and so on, which are quite classic learning materials. Today’s leading role leEMl-Notes is also related to a classic Chinese video course — machine learning by Li Hongyi of National Taiwan University.

directory

  1. Introduction of Li Hongyi machine learning

  2. Machine learning Notes by Hongyi Li

  3. Leeml-notes learning Notes framework

  4. Note content details display

    A. Analysis of the concept of gradient descent

    B. Why do WE need to do feature scaling

    C. The application of invisible Markov chains \

  5. The code presented

    A. Regression analysis

    B. Deep learning

  6. Homework to show

  7. interaction

  8. Open source address \

  9. Accompanying Video \

1. Introduction to Machine learning by Li Hongyi ****

Li Hongyi’s machine learning video is one of the classic Chinese videos in the field of machine learning, and is also known as the best machine learning video in the Chinese world. With his humorous teaching style, Mr. Li made many obscure machine learning theories easy to understand. He combined theoretical knowledge with interesting examples to show in class, and gradually derived esoteric theoretical knowledge to ensure that learners could learn the essence of the problem. For example, teachers often use Pokemon to combine many machine learning algorithms. It is definitely recommended for those who want to get into machine learning and want to see the Chinese explanation.

2. Leeml-notes, Machine Learning Notes by Hongyi Li ****

Lemel-notes is another open source learning project of Datawhale organization. Led by Wang Jiaxu and Jin Yiming, 8 team members polished it carefully for half a year, realizing 100% reproduction of machine learning course content of Teacher Li Hongyi, and supplemented relevant materials and content conducive to learning and understanding on this basis. In addition, the formula of the key and difficult points is derived. During this period, The Datawhale open source organization created a team learning of Machine Learning by Teacher Li Hongyi. With the joint efforts of many learners, the content was iterated and supplemented. Now, let’s take a look at the details of the job.

Specific preparations:

  • February 2019 — April 2019: Primary stage of note collection, 100% video reproduction
  • April 2019 — June 2019: Set up website, iteratively optimized notes content and typesetting
  • May 2019 — June 2019: Learned Li Hongyi Machine Learning in a team and improved the content iteratively
  • July 2019: Final content revision, official promotion.

The following is the revision record table:

3. Leeml-notes learning Notes framework ****

The content is consistent with teacher Li Hongyi’s machine learning course in the overall framework, which is mainly composed of supervised learning, semi-supervised learning, transfer learning, unsupervised learning, structured learning in supervised learning and reinforcement learning. It is suggested to use teacher Li Hongyi’s video with this material during the learning process, and the effect is excellent. The notes are also perfectly synchronized with the lecture videos.

Details of the catalogue are as follows:

Directory * * * *

P1 Introduction to machine learning ****

P2 Why machine learning ****

P3 return * * * *

P4 regression – demo ****

Where does the P5 error come from? * * * *

P6 gradient descent ****

P7 Gradient descent (demonstrated with AOE) ****

P8 Gradient Descent (demonstrated with Minecraft) ****

P9 Exercise 1-PM2.5 prediction ****

P10 Probabilistic classification model ****

P11 Logistic regression ****

P12 Assignment 2- Winner or loser ****

P13 Introduction to deep learning ****

P14 Reverse propagation ****

P15 Preliminary deep learning ****

P16 Keras2.0 * * * *

P17 Keras demo ****

P18 Deep learning techniques ****

P19 Keras Demo 2****

P20 Tensorflow implements Fizz Buzz****

P21 Convolutional neural network ****

P22 Why “deep” Learning? * * * *

P23 Semi-supervised learning ****

P24 Unsupervised learning – Linear dimension reduction ****

P25 Unsupervised learning – Word embedding ****

P26 Unsupervised learning – Domain embedding ****

P27 Unsupervised learning – deep autoencoder ****

P28 Unsupervised learning – Deep generation model I****

P29 Unsupervised learning – Deep generative models II****

P30 Transfer learning ****

P31 Support vector machine ****

P32 Structured Learning – Introduction ****

P33 Structured learning – Linear models ****

P34 Structured learning – Structured Support Vector Machines ****

P35 Structured Learning – Sequence tags ****

P36 Recurrent neural network I****

P37 Recurrent neural network II****

P38 Integrated learning ****

P39 Analysis of deep reinforcement learning ****

P40 The next step in machine learning

4. Note contents and details display ****

4. A analysis of the concept of gradient descent ****

4. Why does b need to do feature scaling ****

4.c The application of invisible Markov chain ****

5. Code presentation ****

The code was optimized on the basis of the code provided by teacher li hongyi and passed all debugging on python3.

5. A regression analysis ****

5.b deep learning ****

6. Homework display ****

This paper explains and interprets the homework of the notes course, and summarizes some points that need to pay attention to. It also passed debugging on python3.

7. Communication and interaction ****

At the end of each section of the directory, there is an interactive exchange area for you to summarize the learning content, put forward your questions and interact with the majority of learners. Just log on to GitHub and it will be convenient for you to communicate.

8. Open source address ****

Github.com/datawhalech…

9. Accompanying video ****

Li Hongyi machine learning video:

www.bilibili.com/video/av595…

Key contributors

Principals: Wang Jiaxu, Jin Yiming

Members: Spades, Li Wei, Ribs, Wind Chaser, Summer, Yang Bingnan

The author’s public id \

Site introduction ↓↓↓

“Machine Learning Beginners” is a personal public account to help artificial intelligence enthusiasts get started (founder: Huang Haiguang)

Beginners on the road to entry, the most need is “help”, rather than “icing on the cake”.

ID: 92416895\

Currently, the planet of Knowledge in the direction of machine learning ranks no. 1.

Past wonderful review \

  • Conscience Recommendation: Introduction to machine learning and learning recommendations (2018 edition) \

  • Github Image download by Dr. Hoi Kwong (Machine learning and Deep Learning resources)

  • Printable version of Machine learning and Deep learning course notes \

  • Machine Learning Cheat Sheet – understand Machine Learning like reciting TOEFL Vocabulary

  • Introduction to Deep Learning – Python Deep Learning, annotated version of the original code in Chinese and ebook

  • The mathematical foundations of machine learning

  • Machine learning essential treasure book – “statistical learning methods” python code implementation, ebook and courseware

  • Blood vomiting recommended collection of dissertation typesetting tutorial (complete version)

  • What if Python code is ugly? Recommend a few artifacts to save you

  • Blockbuster | complete AI learning course, the most detailed resources arrangement!

  • Word2vec

Note: This site’S QQ group: 865189078 (a total of 8 groups, do not add repeatedly).

To join the wechat group of this site, please add the assistant wechat of Huang Bo, explanation: public number user group.

\