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

Korthals T (2019)
arXiv: 1903.07303v1.

Preprint | Englisch
 
Download
OA 262.14 KB
Abstract / Bemerkung
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
Stichworte
Deep Generative Models; Variation Autoencoder; Variation Auto Encoder; Distributed Sensor Network; Sensor Fusion; multi-modal; multi modal; VAE; publication; sensorfusion; fusion
Erscheinungsjahr
2019
Zeitschriftentitel
arXiv: 1903.07303v1
Page URI
https://pub.uni-bielefeld.de/record/2937523

Zitieren

Korthals T. M²VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood. arXiv: 1903.07303v1. 2019.
Korthals, T. (2019). M²VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood. arXiv: 1903.07303v1
Korthals, Timo. 2019. “M²VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood”. arXiv: 1903.07303v1.
Korthals, T. (2019). M²VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood. arXiv: 1903.07303v1.
Korthals, T., 2019. M²VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood. arXiv: 1903.07303v1.
T. Korthals, “M²VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood”, arXiv: 1903.07303v1, 2019.
Korthals, T.: M²VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood. arXiv: 1903.07303v1. (2019).
Korthals, Timo. “M²VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood”. arXiv: 1903.07303v1 (2019).
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
Dieses Objekt ist durch das Urheberrecht und/oder verwandte Schutzrechte geschützt. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-20T16:09:28Z
MD5 Prüfsumme
c3584803a65dda718e11dadcdfd5ae53


Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Quellen

arXiv: 1903.07303v1

Suchen in

Google Scholar