How ageron/handson-ml2 works
This repository is an educational collection for the second edition of *Hands-on Machine Learning*. The learner starts at the notebook index, then works through chapter notebooks covering ML foundations, deep learning, and deployment-scale topics; the intended result is familiarity with the methods and examples. Dataset files support hands-on work, but their specific notebook consumers are not established by the excerpts. Notebook-to-notebook links are therefore omitted rather than inferred as a pipeline.
Main entry points: 01_the_machine_learning_landscape.ipynb Chapters 1–9 · 02_end_to_end_machine_learning_project.ipynb End-to-end project · 03_classification.ipynb Classification · 04_training_linear_models.ipynb Linear models
Components 22
ML foundations
- Chapters 1–9
01_the_machine_learning_landscape.ipynb - End-to-end project
02_end_to_end_machine_learning_project.ipynb - Classification
03_classification.ipynb - Linear models
04_training_linear_models.ipynb - SVMs
05_support_vector_machines.ipynb - Decision trees
06_decision_trees.ipynb - Ensembles
07_ensemble_learning_and_random_forests.ipynb - Dimensionality reduction
08_dimensionality_reduction.ipynb - Unsupervised learning
09_unsupervised_learning.ipynb
Deep learning
- Keras neural nets
10_neural_nets_with_keras.ipynb - Deep network training
11_training_deep_neural_networks.ipynb - Custom TensorFlow
12_custom_models_and_training_with_tensorflow.ipynb - Data preprocessing
13_loading_and_preprocessing_data.ipynb - Computer vision
14_deep_computer_vision_with_cnns.ipynb - Sequence models
15_processing_sequences_using_rnns_and_cnns.ipynb - NLP and attention
16_nlp_with_rnns_and_attention.ipynb - Autoencoders and GANs
17_autoencoders_and_gans.ipynb
Advanced applications
- Reinforcement learning
18_reinforcement_learning.ipynb - Scale and deployment
19_training_and_deploying_at_scale.ipynb
Learning resources
- Notebook index
index.ipynb - Example datasets
datasets
Other components
- Learner
Connections 20
- Learner → Notebook index: opens
README.md - Learner → Chapters 1–9: studies
README.md - Learner → End-to-end project: studies
README.md - Learner → Classification: studies
README.md - Learner → Linear models: studies
README.md - Learner → SVMs: studies
README.md - Learner → Decision trees: studies
README.md - Learner → Ensembles: studies
README.md - Learner → Dimensionality reduction: studies
README.md - Learner → Unsupervised learning: studies
README.md - Learner → Keras neural nets: studies
README.md - Learner → Deep network training: studies
README.md - Learner → Custom TensorFlow: studies
README.md - Learner → Data preprocessing: studies
README.md - Learner → Computer vision: studies
README.md - Learner → Sequence models: studies
README.md - Learner → NLP and attention: studies
README.md - Learner → Autoencoders and GANs: studies
README.md - Learner → Reinforcement learning: studies
README.md - Learner → Scale and deployment: studies
README.md