Introduction to RBM for written digits recognition

Sergey Kharagorgiev (Computer vision engineer, self-employed)
"Introduction to RBM for written digits recognition"

Resticted bolzmann machine (RBM) is a type of a stochastic neural network. It can be used as a building block for deep learning algorithms. One of the great examples of RBM applications is unsupervised features learning for hand-written digits. Not going deep into the theory, let's look at RBM structure, and walk through the basic learning algorithm (so-called Contrastive Divergence).

Slides

Demo
Chapter 5 from Learning Deep Architectures for AI
And classical G.Hinton papers:
A fast learning algorithm for deep belief nets
Training Products of Experts by Minimizing Contrastive Divergence
A Practical Guide to Training Restricted Boltzmann Machines