fengdu78/Coursera-ML-AndrewNg-Notes

吴恩达老师的机器学习课程个人笔记

What it solves

This project provides comprehensive, community-translated Chinese study materials for Andrew Ng’s classic 2014 Stanford Machine Learning course. It bridges the language gap for Chinese-speaking students, offering structured notes that simplify complex theoretical concepts into accessible learning modules.

How it works

The repository organizes the 10-week course curriculum into structured Markdown, HTML, and Word documents. It includes translated subtitles for the video lectures, original course slides (PPTs), and Python code implementations. The content covers the full spectrum of the course, from foundational linear regression and neural networks to advanced topics like anomaly detection and recommender systems.

Who it’s for

This is for students, developers, and AI enthusiasts who want to learn the fundamentals of machine learning using high-quality Chinese-language resources. It is ideal for those who prefer reading structured notes alongside video lectures to reinforce their understanding of algorithms and mathematical foundations.

Highlights

  • Complete 10-week curriculum notes in Markdown, HTML, and Word formats.
  • Includes original course PPT slides and translated Chinese/English subtitles.
  • Provides Python code implementations for course exercises.
  • Offers an online reading version for easy access to formulas and content.
  • Supported by an active community and dedicated discussion groups.

Related

  • Project
    huggingface/pytorch-image-models

    timm (PyTorch Image Models) is a library that provides hundreds of pre‑trained vision architectures (CNNs, Vision Transformers, hybrids, etc.) together with training scripts, optimizers, schedulers, data utilities, and hyper‑parameter sweep tools, all built on PyTorch for easy experimentation and deployment.

  • Project
    jax-ml/jax

    JAX is a Python library for high‑performance, accelerator‑aware numerical computing. It adds composable transformations—automatic differentiation (`grad`), just‑in‑time compilation (`jit`), and auto‑vectorisation (`vmap`)—to NumPy code, and provides parallel‑execution APIs for scaling across many GPUs/TPUs. Install via pip (CPU, CUDA, TPU, ROCm, etc.) and cite the project if used in research.

  • Project
    hpcaitech/ColossalAI

    Colossal-AI is an open-source system that makes training and running large AI models cheaper and faster through advanced parallel computing techniques, supporting models like LLaMA, GPT, and Stable Diffusion across multiple GPUs.

  • Project
    deepspeedai/DeepSpeed

    DeepSpeed is a PyTorch‑based open‑source library that provides memory‑efficient optimizers, multi‑dimensional parallelism, and hardware‑offload engines to train extremely large deep‑learning models (up to hundreds of billions of parameters) on GPUs, CPUs, and specialized accelerators.