Yüklüyor......

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...

Ful tanımlama

Kaydedildi:
Detaylı Bibliyografya
Yayımlandı:Entropy (Basel)
Asıl Yazarlar: Lavda, Frantzeska, Gregorová, Magda, Kalousis, Alexandros
Materyal Türü: Artigo
Dil:Inglês
Baskı/Yayın Bilgisi: MDPI 2020
Konular:
Online Erişim: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
Etiketler: Etiketle
Etiket eklenmemiş, İlk siz ekleyin!