yanshengjia/ml-road

★ 4,775PythonAudience · researcherComplexity · 1/5Setup · easy

Mindmap

mindmap
  root((ml-road))
    Content Types
      University courses
      Textbooks
      Practice code
      Research papers
    Topics Covered
      Deep learning
      Computer vision
      NLP
      Reinforcement learning
    Sources
      Stanford CMU Oxford
      YouTube Coursera
      TensorFlow PyTorch
    Audience
      ML beginners
      Students
      Self-learners

mindmap root((ml-road)) Content Types University courses Textbooks Practice code Research papers Topics Covered Deep learning Computer vision NLP Reinforcement learning Sources Stanford CMU Oxford YouTube Coursera TensorFlow PyTorch Audience ML beginners Students Self-learners

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Browse a table of free university ML courses from Stanford, CMU, and Oxford to pick your next learning resource.

USE CASE 2

Find recommended textbooks and reading material to supplement online deep learning and NLP courses.

USE CASE 3

Discover coding exercises for frameworks like TensorFlow and PyTorch to practice what you are learning.

Tech stack

PythonTensorFlowPyTorch

Getting it running

Difficulty · easy Time to first run · 5min

In plain English

This repository is a curated collection of learning resources for machine learning and AI, assembled as a personal study roadmap. It gathers courses, textbooks, research papers, tutorials, and practice code in one place for anyone trying to learn the field systematically. The bulk of the content is a large table of online courses from universities and organizations including Stanford, UC Berkeley, Carnegie Mellon, Oxford, NYU, and National Taiwan University. The courses cover a range of topics: general machine learning, deep learning, computer vision, natural language processing, reinforcement learning, and working with specific frameworks like TensorFlow and PyTorch. Most entries link to free recordings on YouTube, Bilibili, Coursera, or institutional homepages. Instructors include well-known figures in the field such as Andrew Ng, Fei-Fei Li, Christopher Manning, and Yann LeCun. Beyond courses, the repository collects books and reading material, along with practical coding exercises. The description mentions agentic AI as a newer addition, which refers to systems where AI models take sequences of actions or use tools to complete goals, a growing area of research and application. The repository is intended for educational use only. The maintainer notes that any ebook content belongs to its respective authors and asks that anyone with a copyright concern get in touch. For someone new to machine learning, this kind of curated list can serve as a starting point for figuring out where to begin. Rather than searching independently for what to study, you can browse the course table and pick a starting point based on topic or institution. The repository does not contain a structured curriculum or tell you what order to follow, it is more of a reference catalog than a guided path.

Copy-paste prompts

Prompt 1

Based on the ml-road course list, suggest a learning path for a complete beginner who wants to understand deep learning in 3 months, starting with the Andrew Ng courses.

Prompt 2

Which courses in the ml-road collection cover natural language processing, and are they available free on YouTube or Coursera?

Prompt 3

I want to learn reinforcement learning, which courses in ml-road should I complete as prerequisites, and which RL course should I start with?

Prompt 4

List all courses in the ml-road catalog that use PyTorch rather than TensorFlow and link to free recordings I can watch now.

Open on GitHub → Explain another repo

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

Verify against the repo before relying on details.