English

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 (M2^2VAE).

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

R2 v1 2026-06-23T08:11:05.354Z