Probabilistic machine learning. Introduction
This classic work contains a thorough modern introduction to machine learning (including deep learning), viewed through the unifying prism of probabilistic modeling and Bayesian decision theory. The basic mathematical apparatus (including elements of linear algebra and optimization theory), the basics of teaching with a teacher (including linear and logistic regression and deep neural networks), as well as more complex topics (including transfer of training and teaching without a teacher) are included. The exercises at the end of the chapters will help readers apply their knowledge, and there is a summary of the notation used in the appendix. The publication is based on Kevin Murphy's 2012 book "Machine Learning: A Probabilistic Perspective". However, this is a completely new work, reflecting many achievements that have happened in this area over the past 10 years.
No reviews found
