Here is a roadmap for learning artificial intelligence from scratch
Whether you are an undergraduate, a graduate student, or a career changer, as long as it is 0 basic, it is very applicable, covering basic knowledge, machine learning, deep learning, computer vision, natural language processing, model compression and optimization, deep learning framework, reinforcement learning, supplementary knowledge, it is really very comprehensive;
Next, I will briefly introduce this artificial intelligence learning roadmap.
First, the basic part
You need to learn the basic concepts of artificial intelligence, Python and the basics of mathematics
Basic concepts of artificial intelligence need to know:
- Common AI processes
- What is machine learning vs deep learning?
- What is the difference between supervised learning, unsupervised learning, and reinforcement learning
Python needs to learn:
- The Python runtime environment and the development environment are built
- Python basics
- Python functions
- Python object-oriented programming
- Python scientific computing
Data fundamentals need to be learned:
- Advanced Mathematics
- linear algebra
- probability theory
- Optimal solution
This part recommends Python rookie tutorial documentation, Python basic tutorial
With the book "Mathematics in Vernacular Machine Learning"
Among them, the basic part of the Python rookie documentation only needs to learn the built-in function part;
Python Scientific Computing section recommended books
If you are interested in artificial intelligence, you can blog and then reply to [Learn] in a private message to get a set of introductory learning tutorials
Second, machine learning
Once we have mastered the basics and the use of tools, we can start learning machine learning
Machine Learning recommends Mr. Ng Ng's machine learning manual
Teacher Li Hang's statistical learning method
There is also teacher Zhou Zhihua's machine learning and illustrated machine learning
Since Mr. Li Hang's statistical learning method involves some formula derivation, if you can't understand it, students can give priority to studying other books;
Regarding the practical part of machine learning, it is recommended to take a look at the various completed competition tasks on the Kaggle competition website and learn more about the code of various gods
If you find English difficult, you can also read it
If you are interested in artificial intelligence, you can follow the blogger and send a private message [Learn] to get a set of introductory learning tutorials
Third, deep learning
Next, I began to learn deep learning, and the flower book known as the "Bible" here is not recommended for everyone to read
Deep learning also has no book that can talk about image recognition, natural language processing, and model optimization very comprehensively, the best way is to read a large number of papers, plus project practice, and read the project source code;
However, for the sake of 0 basic students, it is also recommended here that it is convenient to get started
Specifically about image recognition, the convolutional neural network part must have the following network models:
Specific to image recognition object detection must be understood, FasterRCNN, Yolo series
Then I'll look at other aspects
Regarding natural language processing, you finally need to understand some big models, such as Transformer, Google Bert, OpenAI GPT
This requires some basic knowledge upfront
After understanding the NLP big model, then study the application of NLP in other directions
In addition, deep learning should not forget to learn model optimization and deep learning frameworks
This recommended book on project operation
Fourth, reinforcement learning
In recent years, deep reinforcement learning has become more and more popular, and many well-known large models have begun to introduce reinforcement learning to train models, so it is also necessary to learn reinforcement learning
Fifth, supplementary knowledge
If the previous ones have been studied and understood, you can learn about it
Finally, how do you see how well you are learning?
Today's dry goods are shared here, thank you for reading, I hope to help you,
Article creation is not easy, if you like my sharing, don't forget to like and forward, so that more people in need can see,
Finally, don't forget to pay attention to Xiaobian, your support will be the biggest motivation for me to share, I will continue to output more content in the future, so stay tuned
At the same time, a wealth of artificial intelligence learning materials have been prepared to help everyone's learning needs, and the partners who need it can receive it by replying to [Learning] by private message