explaingit

tangyudi/ai-learn

12,978Audience · generalComplexity · 2/5Setup · easy

TLDR

A Chinese-language step-by-step guide to learning AI from scratch, with 200 hands-on examples covering Python, math, machine learning, deep learning, computer vision, and NLP, built by a teacher over five years.

Mindmap

mindmap
  root((AI Learn))
    Learning Path
      Python basics
      Math foundations
      ML algorithms
      Deep learning
    Libraries
      NumPy Pandas
      TensorFlow PyTorch
      OpenCV
    Projects
      Churn prediction
      Titanic survival
      Hotel recommender
    Audience
      Chinese beginners
      Job seekers
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Things people build with this

USE CASE 1

Work through a structured AI learning roadmap in Chinese, progressing from Python basics to practical ML and deep learning projects.

USE CASE 2

Practice machine learning algorithms like decision trees, SVMs, and gradient boosting using real datasets and complete working code.

USE CASE 3

Prepare for AI technical job interviews in the Chinese tech industry using the project-level examples that mirror common interview topics.

Tech stack

PythonNumPyPandasTensorFlowPyTorchKerasOpenCVMatplotlib

Getting it running

Difficulty · easy Time to first run · 30min

Some datasets and supplementary materials are distributed via Chinese cloud storage links that may require a Chinese account to access.

In plain English

Ai-Learn is a Chinese-language guide to learning artificial intelligence from scratch, organized as a step-by-step learning roadmap. The repository was put together by a teacher who developed and refined roughly 200 hands-on examples over five years of in-person and online instruction. Each example uses real datasets, and the materials progress from the very basics to practical projects. The suggested starting path covers Python programming, essential math (calculus, linear algebra, probability and statistics), and the Python libraries most commonly used in AI work: NumPy for matrix operations, Pandas for data handling, Matplotlib and Seaborn for visualization. The roadmap then moves through machine learning algorithms such as linear regression, logistic regression, decision trees, support vector machines, clustering, and boosting methods. Each algorithm section includes code, experiment comparisons, and working examples. After the machine learning section, the roadmap covers deep learning using TensorFlow 2, PyTorch, Keras, and Caffe, followed by computer vision (with OpenCV) and natural language processing. Each area has project-level examples rather than toy code: predictive modeling on census income data, hotel recommendation systems, user churn prediction, Titanic survival classification, and others. A free electronic version of the author companion book is available from the main repository page. The book was written over two years and revised more than ten times. Some supplementary materials such as datasets, slides, and code bundles are shared via Chinese cloud storage links in the README. The repository is aimed at Chinese-speaking beginners who want to move from zero knowledge into practical AI work without wasted detours. The content is also useful for job-interview preparation, since many of the examples mirror common technical interview topics in the Chinese tech industry.

Copy-paste prompts

Prompt 1
I am working through the ai-learn curriculum and I have finished the Python section. Explain this linear regression example and how I can adapt it to a new dataset.
Prompt 2
I am on the deep learning section of ai-learn using PyTorch. Help me understand this training loop and how to modify it for my own image classification task.
Prompt 3
I want to build a user churn prediction model like the one in ai-learn. Walk me through the steps from loading data to training and evaluating the model.
Prompt 4
I am using the ai-learn roadmap but struggling with the math prerequisites. Explain the intuition behind gradient descent without heavy formulas.
Prompt 5
I finished the machine learning section of ai-learn and I want to move into computer vision with OpenCV. What should I focus on first and which examples in the repo cover it?
Open on GitHub → Explain another repo

← tangyudi on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.