Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition

Machine learning becomes easier to approach when its ideas are tied to the decisions made in a real project. Aurélien Géron’s Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow builds that connection, moving from foundational concepts and practical workflows to neural networks and deep learning with Python tools.

This second edition ranges from data preparation and model evaluation to TensorFlow 2 and Keras. It offers readers a structured way to explore both established machine-learning methods and the neural-network techniques that build on them.

Start with the shape of a machine-learning problem

The opening chapters explain what machine learning is, distinguish major types of learning systems, and examine challenges such as poor-quality or unrepresentative data, overfitting, and underfitting. A detailed end-to-end project then shows how problem framing, performance measures, data exploration, preparation, model selection, and evaluation fit together.

Compare practical approaches, not just algorithms

Coverage includes classification and regression, linear models, support vector machines, decision trees, ensemble learning, random forests, dimensionality reduction, and unsupervised methods such as clustering and Gaussian mixtures. Seeing these approaches within a broader workflow can help readers understand where different tools fit and what trade-offs model selection involves.

Move from machine learning to neural networks

The second part introduces artificial neural networks and develops the subject through Keras and TensorFlow 2. Topics include building models, training deep neural networks, optimization, regularization, and custom models and training with TensorFlow. The progression gives readers a route from the fundamentals of neural networks toward more involved deep-learning concepts.

For readers who want concepts alongside code

The contents pair conceptual discussion with practical implementation topics and exercises. The book may suit Python programmers, students, and practitioners seeking a broad, organized introduction to machine learning methods and neural networks, especially readers who want to understand how a project moves from raw data toward model evaluation.

Explore machine learning as a connected discipline—from choosing an approach and preparing data to training and assessing models—with this detailed guide from O’Reilly Media.