Diving in into the Model with GPy

Lately we looked at GPy using some simple examples. Now we’ll dive deeper and look more closely to the inner workings of models. We’ll start with the basics and continue further by decomposing the Guassian Process Latent Variable model (GPLVM). Note: This post is fairly specific to GPy and the chosen model. Investigating parameters All GPy models extend the Parameterized class. This base class gives us several useful functions for interacting with the model parameters....

First steps with GPy

A random process, a collection of random variables, is said to be a Gaussian process (GP)1 if any finite number of these variables have a joint Gaussian distribution; i.e. the relation between variables follows a Gaussian distribution, this says something about the smoothness of functions generated by these processes. Guassian processes are used for many tasks in machine learning; from classification to regression and latent variable models. A lot of work on this subject is done by the machine learning group at the University of Sheffield which maintain and develop the GPy package: a framework, written in python, for GP’s....