Do the 30-D codes found by the autoencoder preserve the class structure of the data?
The fastest possible way to find similar documents
Finding binary codes for documents
How good is a shortlist found this way?
Comparison with hidden Markov models
Generating from a learned model
An early application (Sutskever)
An application to modeling
motion capture data
An RBM with real-valued
visible units
(you don’t have to understand this slide!)
Modeling multiple types of motion
Statistical language modelling
An application to language modeling
How to compute a predictive distribution across 17000 words.