# Probabilistic Machine Learning: An Introduction

Source: https://listme.name/books/probabilistic-machine-learning
Website: https://probml.github.io/pml-book/book1.html

Probability-based machine learning textbook with a free draft PDF

Probabilistic Machine Learning: An Introduction is a 2022 MIT Press textbook by Kevin P. Murphy. It builds machine learning on probability and Bayesian reasoning, with figures that come with reproducible code. A free draft PDF is published under a non-commercial, no-derivatives license.

The book covers supervised and unsupervised learning, state-space models and deep learning under one probabilistic framework. Each model uses the same notation for inference and uncertainty, which makes the methods easier to compare. The site links a short and a long table of contents and a diff against the author's 2012 book.

The draft PDF is free to download, and the author asks readers to report errors through the site. Colab notebooks reproduce most figures, which helps readers who want to test the methods. The text assumes calculus, linear algebra and some probability, so it suits advanced undergraduates and graduate students more than readers new to mathematics.

- Free | PDF/Print
- Price: Free draft PDF; hardcopy sold by MIT Press
- Checked: 2026-10-10

## Strengths

- Free draft PDF and reproducible figure code
- One probabilistic framework for many models
- Published in 2022, after the author's 2012 text

## Limits

- Long and mathematical for self-study
- Free draft carries a non-commercial, no-derivatives license

## Rankings

- #2 of 13 in [best AI and machine learning books](https://listme.name/best/ai-and-machine-learning-books), score 92.5: A broad, current treatment of machine learning as probabilistic modeling, with a free draft PDF. It is more mathematical than the practical texts here and newer than Bishop's 2006 book.

## Alternatives

- [Deep Learning](https://listme.name/books/deep-learning-book), score 94.5
- [Dive into Deep Learning](https://listme.name/books/dive-into-deep-learning), score 91.0
- [An Introduction to Statistical Learning (Python edition)](https://listme.name/books/introduction-to-statistical-learning), score 90.0
- [Deep Learning with Python, Third Edition](https://listme.name/books/deep-learning-with-python), score 88.5
- [Hands-On Machine Learning](https://listme.name/books/hands-on-machine-learning), score 87.0
- [Mathematics for Machine Learning](https://listme.name/books/mathematics-for-machine-learning), score 85.5
- [Build a Large Language Model (From Scratch)](https://listme.name/books/build-a-large-language-model-from-scratch), score 85.0
- [Pattern Recognition and Machine Learning](https://listme.name/books/pattern-recognition-and-machine-learning), score 84.0