What is contrastive divergence? - Quora: "Contrastive divergence is a recipe for training undirected graphical models (a class of probabilistic models used in machine learning). It relies on an approximation of the gradient (a good direction of change for the parameters) of the log-likelihood (the basic criterion that most probabilistic learning algorithms try to optimize) based on a short Markov chain (a way to sample from probabilistic models) started at the last example seen. It has been popularized in the context of Restricted Boltzmann Machines (Hinton & Salakhutdinov, 2006, Science), the latter being the first and most popular building block for deep learning algorithms. Its pseudo-code is very simple; you can see an example implementation in the deep learning tutorial there (in python):"
'via Blog this'