Pattern Recognition and Machine Learning

Pattern Recognition and Machine Learning

Pattern recognition started in engineering, while machine learning came from computer science. However, these activities can be seen as two sides of the same area, and together they have grown a lot in the last ten years. Bayesian methods have moved from being a specialized area to becoming widely used, and graphical models have become a common way to describe and use probabilistic models.

Also, the real-world use of Bayesian methods has become much easier because of new approximate inference techniques like variational Bayes and expectation propagation. New models that use kernels have made a big difference in both the methods used and the real-world uses.

This new textbook addresses recent changes and offers a full introduction to the areas of pattern recognition and machine learning. It is designed for advanced undergraduates or first-year PhD students, as well as researchers and practitioners, and does not require any prior knowledge of pattern recognition or machine learning concepts.

To understand this book, you need to know multivariate calculus and basic linear algebra. It would also be helpful if you have some knowledge of probability, but it’s not required because the book includes its own introduction to basic probability theory.