TY - GEN AB - 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). DA - 2019 KW - Deep Generative Models KW - Variation Autoencoder KW - Variation Auto Encoder KW - Distributed Sensor Network KW - Sensor Fusion KW - multi-modal KW - multi modal KW - VAE KW - publication KW - sensorfusion KW - fusion LA - eng PY - 2019 TI - MĀ²VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood UR - https://nbn-resolving.org/urn:nbn:de:0070-pub-29375235 Y2 - 2024-11-22T04:35:39 ER -