M$^2$VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood

Add code
Mar 18, 2019
Timo Korthals
Figure 1 for M$^2$VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood
Figure 2 for M$^2$VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

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).

* Appendix for the IEEE FUSION 2019 submission on multi-modal variational Autoencoders for sensor fusion  
View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon