English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Hierarchical Variational Autoencoders (VAEs) are among the most popularlikelihood-based generative models. There is a consensus that the top-downhierarchical VAEs allow effective learning of deep latent structures and avoidproblems like posterior collapse. Here, we show that this is not necessarilythe case, and the problem of collapsing posteriors remains. To discourage thisissue, we propose a deep hierarchical VAE with a context on top. Specifically,we use a Discrete Cosine Transform to obtain the last latent variable. In aseries of experiments, we observe that the proposed modification allows us toachieve better utilization of the latent space and does not harm the model'sgenerative abilities.

Discouraging posterior collapse in hierarchical Variational Autoencoders using context