Generalized Stochastic Backpropagation

no code implementations • 1 Jan 2021 • Amine Echraibi, Joachim Flocon Cholet, Stéphane Gosselin, Sandrine Vaton

Backpropagating gradients through random variables is at the heart of numerous machine learning applications.

On the Variational Posterior of Dirichlet Process Deep Latent Gaussian Mixture Models

no code implementations • 16 Jun 2020 • Amine Echraibi, Joachim Flocon-Cholet, Stéphane Gosselin, Sandrine Vaton

Thanks to the reparameterization trick, deep latent Gaussian models have shown tremendous success recently in learning latent representations.