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

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

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).

Timo Korthals

[1] Masahiro Suzuki,et al. Joint Multimodal Learning with Deep Generative Models , 2016, ICLR.

[2] Max Welling,et al. Auto-Encoding Variational Bayes , 2013, ICLR.