M$^2$VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood
Machine Learning
2019-03-19 v1 Machine Learning
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 (MVAE).
Keywords
Cite
@article{arxiv.1903.07303,
title = {M$^2$VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood},
author = {Timo Korthals},
journal= {arXiv preprint arXiv:1903.07303},
year = {2019}
}
Comments
Appendix for the IEEE FUSION 2019 submission on multi-modal variational Autoencoders for sensor fusion