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

While convolutional neural networks need large labeled sets for trainingimages, expert human supervision of such datasets can be very laborious.Proposed solutions propagate labels from a small set of supervised images to alarge set of unsupervised ones to obtain sufficient truly-and-artificiallylabeled samples to train a deep neural network model. Yet, such solutions needmany supervised images for validation. We present a loop in which a deep neuralnetwork (VGG-16) is trained from a set with more correctly labeled samplesalong iterations, created by using t-SNE to project the features of its lastmax-pooling layer into a 2D embedded space in which labels are propagated usingthe Optimum-Path Forest semi-supervised classifier. As the labeled set improvesalong iterations, it improves the features of the neural network. We show thatthis can significantly improve classification results on test data (using only1\% to 5\% of supervised samples) of three private challenging datasets and twopublic ones.

Semi-supervised deep learning based on label propagation in a 2D embedded space