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 propose two generic methods for improving semi-supervised learning (SSL).The first integrates weight perturbation (WP) into existing "consistencyregularization" (CR) based methods. We implement WP by leveraging variationalBayesian inference (VBI). The second method proposes a novel consistency losscalled "maximum uncertainty regularization" (MUR). While most consistencylosses act on perturbations in the vicinity of each data point, MUR activelysearches for "virtual" points situated beyond this region that cause the mostuncertain class predictions. This allows MUR to impose smoothness on a widerarea in the input-output manifold. Our experiments show clear improvements inclassification errors of various CR based methods when they are combined withVBI or MUR or both.

Semi-Supervised Learning with Variational Bayesian Inference and Maximum Uncertainty Regularization