A carregar...

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...

ver descrição completa

Na minha lista:
Detalhes bibliográficos
Publicado no:Entropy (Basel)
Main Authors: Lavda, Frantzeska, Gregorová, Magda, Kalousis, Alexandros
Formato: Artigo
Idioma:Inglês
Publicado em: MDPI 2020
Assuntos:
Acesso em linha:https://ncbi.nlm.nih.gov/pmc/articles/PMC7517502/
https://ncbi.nlm.nih.gov/pubmed/33286658
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.3390/e22080888
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!