Cargando…
Data-Dependent Conditional Priors for Unsupervised Learning of Multimodal Data †
One of the major shortcomings of variational autoencoders is the inability to produce generations from the individual modalities of data originating from mixture distributions. This is primarily due to the use of a simple isotropic Gaussian as the prior for the latent code in the ancestral sampling...
| Autores principales: | , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
MDPI
2020
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7517502/ https://www.ncbi.nlm.nih.gov/pubmed/33286658 http://dx.doi.org/10.3390/e22080888 |