jump to main content

Go to page

Bibliographic Metadata

Title
M²VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood
Author
Korthals, Timo
Published
2019
Language
English
Document type
Preprint
Keywords
Deep Generative Models / Variation Autoencoder / Variation Auto Encoder / Distributed Sensor Network / Sensor Fusion / multi-modal / multi modal / VAE / publication / sensorfusion / fusion
URN
urn:nbn:de:0070-pub-29375235

Restriction-Information

The document is publicly available on the WWW

Links

Social Media

Share
Reference
No Reference available
IIIF
IIIF Manifest

Files

M²VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood [Pdf 0.24 mb]
RIS

Classification

Klassifikation (DDC) → Informatik, Informationswissenschaft, allgemeine Werke → Informatik, Wissen, Systeme → Spezielle Computerverfahren

Abstract

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).

Abstract

Appendix for the IEEE FUSION 2019 submission on multi-modal variational Autoencoders for sensor fusion

Stats

The PDF-Document has been downloaded 5 times.