pith. sign in

arxiv: 1903.07303 · v1 · pith:JK7FZFL4new · submitted 2019-03-18 · 💻 cs.LG · stat.ML

M²VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood

classification 💻 cs.LG stat.ML
keywords autoencoderderivationjointlog-likelihoodmarginalmulti-modalvariationalbound
0
0 comments X
read the original abstract

This work gives an in-depth derivation of the trainable evidence lower bound obtained from the marginal joint log-Likelihood with the goal of training a Multi-Modal Variational Autoencoder (M$^2$VAE).

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.