Source /Datawhale Graphics/retreat typography/Home hao \

【 introduction 】Hands-on Deep Learning was jointly created by Li Mu, chief scientist of Amazon, Aston Zhang, application scientist of Amazon and other masters, which took three years to complete. This book adopts interactive learning method, not only teaches the principle of deep learning algorithm, but also gives the code operation and implementation, so that you can understand and digest the knowledge while manipulating the code.

\

There are often private messages from learners in the background of wechat: They want to learn deep learning, but do not know how to learn it. Do you have any recommended books or experience to impart? \

Anyone who has stepped on a pit should have the following experiences:

Deep learning requires a certain amount of math, and difficult mathematical formulas can be maddening.

Existing data of deep learning tend to be theoretical, abstract and difficult to understand, which is easy to make people confused and unfathomable.

There are more English materials for deep learning video teaching. Although subtitles are added, it is not as comfortable as Chinese.

See here, some people may long sigh, you are to persuade me, I tell you: you succeeded!

Don’t worry, now I’m going to give you a book for deep learning beginners, a good book to help you easily master machine learning.

On June 19th, as a member of Datawhale, Xiaobian attended the AWS Educational Technology Exchange meeting, which was also the new book launch of Hands-on Learning deep Learning. The lead author of this book, Aston Zhang, was invited to communicate with us. In order to better iterate the content, several male science and engineering students entered douyu live broadcast room to communicate and learn with everyone. The book’s 3000 friends in the communication community collected more than 5000 questions, polished them and completed the iteration. The editor of the book also sneaks in that Aston is so strict with the layout that she corrects every single space in the notes and adheres to Pep8 guidelines.

I think it is precisely because of the author’s rigorous attitude and open source spirit that the book has been recommended by Han Jiawei, Bernhard Scholkopf and Zhou Zhihua, etc. It has also been used as a teaching book by 15 world-renowned universities including Berkeley, California, and won the title in the category of Computer and electronic books of Jingdong on June 18. Now let’s take a closer look at this book.

Structure of the book

The first part (chapters 1 to 3) covers preparation and the basics. Chapter 1 introduces the background of deep learning. Chapter 2 provides hands-on preparation for deep learning, such as how to get and run the code in this book. Chapter 3 covers the most basic concepts and techniques of deep learning, such as multilayer perceptrons and model regularization. If time is limited and you just want to understand the most basic concepts and techniques of deep learning, read part 1.

 

The second part (chapters 4-6) focuses on modern deep learning techniques. Chapter 4 describes the various important components of deep learning computing and lays the foundation for implementing more complex models later on. Chapter 5 explains the convolutional neural networks that have made deep learning a great success in computer vision in recent years. Chapter 6 describes the recurrent neural networks which are often used to process sequence data in recent years. Reading Part 2 will help you master modern deep learning techniques.

 

The third part (Chapters 7 to 10) discusses computing performance and applications. Chapter 7 evaluates various optimization algorithms used to train deep learning models. Chapter 8 examines several important factors that affect deep learning computing performance. Chapter 9 and 10 list the important applications of deep learning in computer vision and natural language processing respectively. This section is for readers to read according to their interests.

 

The details can be seen below, which depicts the structure of the book, with the arrows from chapter A to chapter B indicating that the knowledge from Chapter A helps to understand the content of chapter B.

code

The code of this book is based on Apache MXNet, which is an open source deep learning framework. However, it only uses the basic functions of MODULES or packages such as NDARray, Autograd and Gluon of MXNet. Even those who use other deep learning frameworks can use the code in this book to better understand and apply deep learning.

Each section of code in the book can run independently, and will be provided to everyone for free, you can modify according to their own understanding, so as to better understand the logic of the algorithm, really achieve in the text, images and formulas to create an interactive learning environment, better understand learning.

Communication community

discuss.gluon.ai/c/lecture? O… For those who do not understand or think there are problems in the book, you can ask questions in the communication community, and there will be a dedicated person to reply to you. In addition, it is also a good choice to wander around the community and learn from other people’s experience.

Finally, we offer resources:

  • Zh.d2l.ai /index.html
  • GitHub Project: github.com/diveintodee…
  • PDF: useful. D2l. Ai/d2l – useful. PDF
  • Video tutorial: space.bilibili.com/209599371/c…

The author’s public id: \

Site introduction ↓↓↓

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)

  • Installation of Python (Anaconda+Jupyter Notebook +Pycharm)

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

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

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.