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

We formulate a data independent latent space regularisation constraint forgeneral unsupervised autoencoders. The regularisation rests on sampling theautoencoder Jacobian in Legendre nodes, being the centre of the Gauss-Legendrequadrature. Revisiting this classic enables to prove that regularisedautoencoders ensure a one-to-one re-embedding of the initial data manifold toits latent representation. Demonstrations show that prior proposedregularisation strategies, such as contractive autoencoding, cause topologicaldefects already for simple examples, and so do convolutional based(variational) autoencoders. In contrast, topological preservation is ensuredalready by standard multilayer perceptron neural networks when beingregularised due to our contribution. This observation extends through theclassic FashionMNIST dataset up to real world encoding problems for MRI brainscans, suggesting that, across disciplines, reliable low dimensionalrepresentations of complex high-dimensional datasets can be delivered due tothis regularisation technique.

Ensuring Topological Data-Structure Preservation under Autoencoder Compression due to Latent Space Regularization in Gauss--Legendre nodes