M$^2$VAE——从边际联合对数似然推导多模态变分自编码器目标
机器学习
2019-03-19 v1 机器学习
摘要
本工作给出了从边际联合对数似然(marginal joint log-Likelihood)获得的可得训练的证据下界(evidence lower bound)的深入推导,旨在训练多模态变分自编码器(MVAE)。
引用
@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}
}
备注
Appendix for the IEEE FUSION 2019 submission on multi-modal variational Autoencoders for sensor fusion