Intuitive Introduction to Gaussian Processes

A Gaussian Process is a non-parametric model that can be used to represent a distribution over functions. Lets break this definition down. Parametric models assume that the data distribution (set of input points, images etc.) can be entirely defined in terms of a finite set of parameters theta. For example in simple linear regression the parameters are the m and c in the equation y mx c. Such that if the model is given the parameters, a future prediction is independent of the data.