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

Semi-supervised learning plays an important role in large-scale machinelearning. Properly using additional unlabeled data (largely available nowadays)often can improve the machine learning accuracy. However, if the machinelearning model is misspecified for the underlying true data distribution, themodel performance could be seriously jeopardized. This issue is known as modelmisspecification. To address this issue, we focus on generative models andpropose a criterion to detect the onset of model misspecification by measuringthe performance difference between models obtained using supervised andsemi-supervised learning. Then, we propose to automatically modify thegenerative models during model training to achieve an unbiased generativemodel. Rigorous experiments were carried out to evaluate the proposed methodusing two image classification data sets PASCAL VOC'07 and MIR Flickr. Ourproposed method has been demonstrated to outperform a number ofstate-of-the-art semi-supervised learning approaches for the classificationtask.

Towards well-specified semi-supervised model-based classifiers via structural adaptation