[Formula: see text] VAE: a stochastic process prior for Bayesian deep learning with MCMC

Stochastic processes provide a mathematically elegant way to model complex data. In theory, they provide flexible priors over function classes that can encode a wide range of interesting assumptions. However, in practice efficient inference by optimisation or marginalisation is difficult, a problem...

Descripción completa

Detalles Bibliográficos
Autores principales: Mishra, Swapnil, Flaxman, Seth, Berah, Tresnia, Zhu, Harrison, Pakkanen, Mikko, Bhatt, Samir
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer US 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9576140/
https://www.ncbi.nlm.nih.gov/pubmed/36276409
http://dx.doi.org/10.1007/s11222-022-10151-w

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9576140/
https://www.ncbi.nlm.nih.gov/pubmed/36276409
http://dx.doi.org/10.1007/s11222-022-10151-w

Ejemplares similares