Density Networks
David Mackay, M. Gibbs · 2000
Abstract A density network is a neural network that maps from unobserved inputs to observable outputs. The inputs are treated as latent variables so that, for given network parameters, a nontrivial probability density is defined over the output variables. This probabilistic model can be trained by various Monte Carlo methods. The model can discover a description of the observed data in terms of an underlying latent variable space of lower dimensionality. We review results of the application of these models to toy problems with categorical and real-valued observables and to protein data.