Description
Probabilistic Machine Learning: An Introduction offers a detailed and up-to-date introduction to machine learning, including deep learning, through the unifying lens of probabilistic modeling and Bayesian decision theory. The book covers essential mathematical background, including linear algebra and optimization, and explores basic supervised learning techniques such as linear and logistic regression, as well as deep neural networks. More advanced topics, including transfer learning and unsupervised learning, are also discussed.
Read More
End-of-chapter exercises allow students to apply what they have learned, reinforcing their understanding of the material. An appendix provides a comprehensive overview of notation used throughout the text. This book is not merely an update of the author's previous work, Machine Learning: A Probabilistic Perspective, but rather a completely new text that reflects the significant developments in the field since 2012, particularly in deep learning.
Accompanying the book is online Python code that utilizes libraries such as scikit-learn, JAX, PyTorch, and TensorFlow. This code enables readers to reproduce nearly all figures presented in the book, and it can be executed within a web browser using cloud-based notebooks. This practical resource complements the theoretical topics discussed, making it an invaluable tool for learners.
Authored by Kevin P. Murphy, a Research Scientist at Google, this book is aimed at students and professionals interested in artificial intelligence and machine learning. It serves as an introductory text that will be followed by a sequel covering more advanced topics, maintaining the same probabilistic approach.
- CategoryOther AI Tools
Book Details
Author: Kevin P. Murphy
Publication Year: 2022
Pages: 864
Formats Available: Hardcover, eBook
Publisher: The MIT Press
ISBN: 9780262046824
eBook ISBN: 9780262369305
Series: Adaptive Computation and Machine Learning
Who This Book Is For
- Learning Machine Learning
- Deep Learning Applications
- Probabilistic Modeling
- Educational Resource
- Practical Coding
