Download Gaussian Processes for Machine Learning, Gaussian processes (GPs) offer a principled, practical, probabilistic approach to learning in kernel machines. The book deals with the supervised-learning problem for each regression and classification, and includes elaborated algorithms. a wide variety of covariance (kernel) functions are given and their properties mentioned. Model selection is mentioned both from a bayesian and a classical perspective. several connections to different well-known techniques from machine learning and statistics are mentioned, as well as support-vector machines, neural networks, splines, regularization networks, relevance vector machines and others. Download the pdf from below to explore all content and start learning.


1 Introduction
2 Regression
3 Classification
4 Covariance Functions
5 Model Selection and Adaptation of Hyperparameters
6 Relationships between GPs and Other Models
7 Theoretical Perspectives
8 Approximation Methods for Large Datasets
9 Further Issues and Conclusions
Appendix A Mathematical Background
Appendix B Gaussian Markov Processes
Appendix C Datasets and Code