ageron/handson-ml3

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.

What it solves

This project provides the practical, hands-on code examples and exercise solutions for the third edition of the book "Hands-on Machine Learning with Scikit-Learn, Keras and TensorFlow." It bridges the gap between theoretical machine learning concepts and real-world implementation in Python.

How it works

The project consists of a collection of Jupyter Notebooks that you can run to follow along with the book. You can execute these notebooks directly in your browser using cloud services like Google Colab, Kaggle, or Deepnote, or you can set up a local environment on your own computer using Conda and Docker.

Who it’s for

It is designed for students, developers, and data enthusiasts who are reading the third edition of the "Hands-on Machine Learning" book and want to practice the concepts using Scikit-Learn, Keras, and TensorFlow.

Highlights

  • Contains complete example code and solutions for all exercises in the book.
  • Supports multiple execution methods including cloud-based environments (Colab, Kaggle, Binder) and local installations.
  • Provides a standardized environment setup using Conda to ensure compatibility.
  • Includes a Docker configuration for consistent, containerized development.

Related

  • Project
    deeplearning4j/deeplearning4j

    A comprehensive JVM-based deep learning ecosystem that enables building, training, and deploying neural networks using Java, Scala, Kotlin, and Clojure.

  • Project
    mlfoundations/open_clip

    An open-source implementation of OpenAI's CLIP for training and using large-scale contrastive language-image models.

  • Project
    davisking/dlib

    A modern C++ toolkit containing machine learning algorithms and tools for creating complex software to solve real-world problems.

  • Project
    horovod/horovod

    A distributed deep learning training framework that makes it is easy to scale single-GPU training scripts to multiple GPUs and hosts across TensorFlow, PyTorch, Keras, and MXNet.