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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Classic variational autoencoders are used to learn complex datadistributions, that are built on standard function approximators. Especially,VAE has shown promise on a lot of complex task. In this paper, a newautoencoder model - classification supervised autoencoder (CSAE) based onpredefined evenly-distributed class centroids (PEDCC) is proposed. Our methoduses PEDCC of latent variables to train the network to ensure the maximizationof inter-class distance and the minimization of inner-class distance. Insteadof learning mean/variance of latent variables distribution and takingreparameterization of VAE, latent variables of CSAE are directly used toclassify and as input of decoder. In addition, a new loss function is proposedto combine the loss function of classification. Based on the basic structure ofthe universal autoencoder, we realized the comprehensive optimal results ofencoding, decoding, classification, and good model generalization performanceat the same time. Theoretical advantages are reflected in experimental results.

A Classification Supervised Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids