My Notes on Deep Belief Networks

I think the Deep Belief Networks of Hinton et al are quite interesting.. in that they are real science with measurable results that has been reproduced by multiple implementations. The 2006 paper that started it all and Hinton's presentation on google video:

A formal analysis:

Application to natural language processing:

Reproducing Hinton and extension to and evaluation in other domains:

Use in Computer animation of facial expressions:

Most impressive:

A C++ implementation (although it has much Python love):

A Java implementation:

So yeah, there's some pretty good demonstrations of how powerful DBNs are..