ageron/handson-mlp

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, PyTorch, and Hugging Face libraries.

What it solves

This project provides a practical, hands-on environment for learning the fundamentals of machine learning using Python. It serves as the companion code repository for the O'Reilly book "Hands-on Machine Learning with Scikit-Learn and PyTorch," helping readers bridge the gap between theoretical concepts and actual implementation.

How it works

The project consists of a collection of Jupyter notebooks containing example code and solutions to exercises from the book. Users can run these notebooks directly in their web browser via Google Colab without any local setup, or install the environment on their own machine to work locally.

Who it’s for

It is designed for students, developers, and data science enthusiasts who want to learn machine learning through a practical, code-first approach using the Scikit-Learn and PyTorch libraries.

Highlights

  • Includes complete example code and exercise solutions from the book.
  • Offers a "one-click" experience via Google Colab for immediate experimentation.
  • Provides clear installation instructions for local development environments.
  • Includes an FAQ section to help troubleshoot common setup issues like SSL errors or library versions.

Related

  • Project
    wzyonggege/statistical-learning-method

    An educational repository featuring hand-written Python implementations of nine classic statistical learning algorithms, updated for modern compatibility and reproducibility.

  • Project
    tensorflow/tfx

    TensorFlow Extended (TFX) is a production-scale ML platform that provides a framework for building and orchestrating automated machine learning pipelines.

  • Project
    tensorflow/quantum

    TensorFlow Quantum is a Python library that integrates Cirq quantum circuits with TensorFlow/Keras, providing high‑performance hybrid quantum‑classical machine‑learning models, automatic differentiation, and scalable simulation via qsim.

  • Project
    PrimeIntellect-ai/prime-rl

    prime-rl is a framework for large‑scale reinforcement learning, designed for asynchronous RL training at scale. It enables training models on up to 1000+ GPUs with features like FSDP2, vLLM, and support for agentic and multimodal tasks.