# Deep Belief Networks

In this chapter, we're going to present two probabilistic generative models that employ a set of latent variables to represent a specific data generation process. **Restricted Boltzmann Machines** (**RBMs**), proposed in 1986, are the building blocks of a more complex model, called a **Deep Belief Network** (**DBN**), which is capable of capturing complex relationships among features at different levels (in a way not dissimilar to a deep convolutional network). Both models can be used in unsupervised and supervised scenarios as preprocessors or, as is usual with DBN, fine-tuning the parameters using a standard backpropagation algorithm.

In particular, we will discuss:

**Markov random fields**(**MRF**)- RBM, including the
**Contrastive Divergence**(**CD-k**) algorithm - DBN with supervised and unsupervised examples

We can now discuss the fundamental theoretical concept behind this model family: the Markov random fields, showing their properties and how they can be...