On Autoencoders and Score Matching for Energy Based Models

We consider estimation methods for the class of continuous-data energy based models (EBMs). Our main result shows that estimating the parameters of an EBM using score matching when the conditional distribution over the visible units is Gaussian corresponds to training a particular form of regularize...

Szczegółowa specyfikacja

Opis bibliograficzny
Główni autorzy: Swersky, K, Ranzato, M, Buchman, D, Marlin, B, Freitas, N
Format: Conference item
Wydane: ACM 2011