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

Deep generative models often perform poorly in real-world applications due tothe heterogeneity of natural data sets. Heterogeneity arises from datacontaining different types of features (categorical, ordinal, continuous, etc.)and features of the same type having different marginal distributions. Wepropose an extension of variational autoencoders (VAEs) called VAEM to handlesuch heterogeneous data. VAEM is a deep generative model that is trained in atwo stage manner such that the first stage provides a more uniformrepresentation of the data to the second stage, thereby sidestepping theproblems caused by heterogeneous data. We provide extensions of VAEM to handlepartially observed data, and demonstrate its performance in data generation,missing data prediction and sequential feature selection tasks. Our resultsshow that VAEM broadens the range of real-world applications where deepgenerative models can be successfully deployed.

VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data