Probabilistic Machine Learning: An Introduction by Kevin Murphy
Probabilistic Machine Learning: An Introduction - Table of Contents
- 1. Introduction
- PART I: FOUNDATIONS
- 2. Probability: Univariate Models
- 3. Probability: Multivariate Models
- 4. Statistics
- 5. Decision Theory in Machine Learning
- 6. Information Theory
- 7. Linear Algebra
- 8. Optimization
- PART II: LINEAR MODELS
- 9. Linear Discriminant Analysis
- 10. Logistic Regression
- 11. Linear Regression
- 12. Generalized Linear Models (GLMs)
- PART III: DEEP NEURAL NETWORKS
- 13. Deep Neural Networks for Tabular Data
- 14. Neural Networks for Images
- 15. Neural Networks for Sequences
- PART IV: NONPARAMETRIC MODELS
- 16. Exemplar-Based Methods
- 17. Kernel Methods in Machine Learning
- 18. Trees, Forests, Bagging, and Boosting
- PART V: BEYOND SUPERVISED LEARNING
- 19. Learning with Fewer Labeled Examples
- 20. Dimensionality Reduction Techniques
- 21. Clustering
- 22. Recommender Systems
- 23. Graph Embeddings
What You Will Learn in Probabilistic Machine Learning: An Introduction
Probabilistic Machine Learning: An Introduction by Kevin P. Murphy is a state-of-the-art textbook that serves as a modern entry point to probabilistic machine learning. Re-imagining classical machine learning foundations through contemporary computational tools, this text breaks down core topics including probability distributions, linear and logistic regression, deep neural networks, generative adversarial networks (GANs), variational autoencoders (VAEs), and Markov chain Monte Carlo (MCMC) methods into structured, accessible chapters.
Designed for undergraduate and graduate students, machine learning engineers, and quantitative researchers, this book illuminates how probabilistic modeling provides a unified framework for reasoning under uncertainty. Dr. Murphy bridges core theoretical principles with practical software implementations, guiding readers through decision theory, non-parametric models, optimization methods, and deep learning architectures. Whether training convolutional networks or deriving variational bounds, practitioners will find this systematic treatment invaluable.
Praised worldwide for its pedagogical clarity, up-to-date scope, and rich visual illustrations, it represents one of the best probabilistic machine learning introduction books pdf available for self-study. It systematically equips learners with necessary analytical tools for mastering modern probabilistic AI with confidence.
Book Details & Specifications
Title:
Probabilistic Machine Learning: An Introduction by Kevin Murphy
Publisher:
The MIT Press
Year:
2022
Pages:
860
Type:
PDF
Language:
English
ISBN-10 #:
0262046822
ISBN-13 #:
978-0262046824
License:
CC BY-NC-ND 4.0
Amazon:
Amazon
About the Author: Kevin Patrick Murphy
The author Kevin Patrick Murphy
is a Senior Research Scientist at Google DeepMind, where he focuses on probabilistic generative models, deep learning, and Bayesian neural networks. He holds a Ph.D. in Computer Science from UC Berkeley and previously served as a Professor of Computer Science and Statistics at the University of British Columbia.
A globally recognized authority in artificial intelligence, Dr. Murphy's influential research covers probabilistic graphical models, automated Bayesian inference, and deep generative architectures. His textbooks are widely adopted across top university curricula and research labs worldwide.
Read or Downloadable Probabilistic Machine Learning: An Introduction
Free Statistical Learning & Machine Learning Books PDF