Skip to main content
Recurrent Exponential-Family Harmoniums without Backprop-Through-Time
Abstract
Exponential-family harmoniums (EFHs), which extend restricted Boltzmannmachines (RBMs) from Bernoulli random variables to other exponential families(Welling et al., 2005), are generative models that can be trained withunsupervised-learning techniques, like
Many UC-authored scholarly publications are freely available on this site because of the UC's open access policies. Let us know how this access is important for you.