
As an Amazon Associate and affiliate partner, Menrva Books earns from qualifying purchases. Learn more
A detailed and up-to-date introduction to machine learning, presented through the unifying lens of probabilistic modeling and Bayesian decision theory. This book 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 mathematical background (including linear algebra and optimization), basic supervised learning (including linear and logistic regression and deep neural networks), as well as more advanced topics (including transfer learning and unsupervised learning). End-of-chapter exercises allow students to apply what they have learned, and an appendix covers notation. Probabilistic Machine Learning grew out of the author’s 2012 book, Machine Learning: A Probabilistic Perspective. More than just a simple update, this is a completely new book that reflects the dramatic developments in the field since 2012, most notably deep learning. In addition, the new book is accompanied by online Python code, using libraries such as scikit-learn, JAX, PyTorch, and Tensorflow, which can be used to reproduce nearly all the figures; this code can be run inside a web browser using cloud-based notebooks, and provides a practical complement to the theoretical topics discussed in the book. This introductory text will be followed by a sequel that covers more advanced topics, taking the same probabilistic approach.
This book introduces the fundamental principles of machine learning through the lens of probabilistic modeling and Bayesian decision theory. The author, Kevin P. Murphy, a recognized expert in the field, presents a comprehensive overview that includes essential mathematical background, foundational supervised learning techniques, and advanced topics such as deep learning and transfer learning. The text is designed to be accessible to students, offering end-of-chapter exercises and an appendix on notation, while also providing practical implementation through accompanying Python code. This work builds upon the author's previous book but is a completely new text reflecting significant advancements in machine learning since 2012.
This introductory text is positioned as a detailed and up-to-date resource for machine learning, emphasizing a probabilistic approach. The inclusion of Python code and cloud-based notebooks suggests a focus on practical application alongside theoretical understanding. The book's structure, building from foundational concepts to more advanced topics, indicates its suitability for students and researchers seeking a comprehensive overview of modern machine learning techniques. Its development from a prior work and its commitment to reflecting recent advancements, particularly in deep learning, signal its relevance in a rapidly evolving field.
Page Count:
864
Publication Date:
2022-03-01
Publisher:
MIT Press
ISBN-10:
0262046822
ISBN-13:
9780262046824
No comments yet. Be the first to share your thoughts!