ageron/handson-ml3 ? reverse-engineered prompt

Build me a Jupyter notebook project that teaches the basics of machine learning and deep learning in Python, following the style of a hands on course or book companion.

I want a clear landing notebook that links out to a full set of lessons, starting with the basics and then moving through classification, regression, support vector machines, decision trees, ensembles, dimensionality reduction, unsupervised learning, neural networks with Keras and TensorFlow, data loading and preprocessing, computer vision, sequences, NLP, autoencoders, reinforcement learning, and scaling and deployment topics.

Each notebook should be easy to read, mix explanation with runnable code, and include example data, visualizations, and exercises or practice sections where it makes sense. Please also include the setup files so someone can run everything locally in a notebook environment, plus a simple Docker option if that fits naturally. If you need to look up current library docs online, go ahead.