allmachinelearning/machinelearning

★ 3,797Audience · researcherComplexity · 1/5Setup · easy

Mindmap

mindmap
  root((ML Reading List))
    Learning path
      Intro textbook
      Neural networks
      Hands-on Python
    Specialties
      Deep learning
      Computer vision
      NLP
      Reinforcement learning
    Prerequisites
      Linear algebra
      Probability
      Python libraries
    Resources
      University courses
      Online lectures
      Survey papers

mindmap root((ML Reading List)) Learning path Intro textbook Neural networks Hands-on Python Specialties Deep learning Computer vision NLP Reinforcement learning Prerequisites Linear algebra Probability Python libraries Resources University courses Online lectures Survey papers

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Find a structured learning path from zero to machine learning practitioner using Chinese-language books and courses.

USE CASE 2

Discover curated resources for specialty areas like deep learning, computer vision, or reinforcement learning.

USE CASE 3

Locate math prerequisite materials for linear algebra and probability before diving into ML coursework.

Tech stack

PythonTensorFlowPyTorchScikit-learn

Getting it running

Difficulty · easy Time to first run · 5min

In plain English

This repository is a curated reading list for people who want to learn machine learning, with almost all content written in Chinese. It is not a software project you install or run, it is a collection of links, notes, and pointers to books, online courses, and datasets organized by topic. The list opens with a suggested learning path. It recommends starting with a widely read Chinese textbook on machine learning for a broad overview, then moving to a neural-networks text for deeper theory, and using Python code examples from a companion book to get hands-on practice. It also points to lecture series from universities in Taiwan and China, Andrew Ng's well-known Coursera course, and graduate-level courses from Carnegie Mellon University for people who want serious mathematical depth. Beyond introductory material, the list branches into specialty areas. There are sections covering deep learning, reinforcement learning, transfer learning (applying knowledge from one task to another), distributed learning systems, computer vision, natural language processing, and bioinformatics. Each specialty section links out to another curated list maintained elsewhere on GitHub. The prerequisite section is useful for beginners. It points to resources on linear algebra, probability, and statistics, and includes cheat sheets for Python libraries like NumPy, SciPy, Pandas, and Matplotlib. It also lists the major deep learning frameworks in Python, Java, and Matlab, including TensorFlow, PyTorch, Keras, Scikit-learn, Caffe, and MXNet, so readers know what tools the field uses before they start coding. A notes section collects survey papers, introductory documents, and slides from talks on topics like human-computer interaction and the history of machine learning. The repository is designed as an entry point and ongoing reference, not a self-contained curriculum. Someone with no background in the field can use it to find where to start, someone already learning can use it to find resources on a specific subfield.

Copy-paste prompts

Prompt 1

I want to follow the learning path in this repo. I have finished the introductory textbook. Help me build a 4-week study plan using the neural networks text and the Python hands-on book mentioned in the list.

Prompt 2

Based on the specialty sections in this repo, help me decide whether to focus on computer vision or NLP next, and list the first three resources I should work through from the relevant section.

Prompt 3

Using the Python libraries listed as prerequisites in this repo (NumPy, Pandas, Matplotlib), help me write a script that loads a CSV dataset, cleans it, and plots a histogram of one column.

Prompt 4

I want to learn reinforcement learning using resources from this list. Summarize what the linked curated RL list covers and suggest a project I can build after finishing the basics.

Prompt 5

Walk me through the difference between TensorFlow, PyTorch, and Scikit-learn as listed in this repo, and tell me which one a complete beginner should start with and why.

Open on GitHub → Explain another repo

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

Verify against the repo before relying on details.