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

Deep neural networks are powerful, massively parameterized machine learningmodels that have been shown to perform well in supervised learning tasks.However, very large amounts of labeled data are usually needed to train deepneural networks. Several semi-supervised learning approaches have been proposedto train neural networks using smaller amounts of labeled data with a largeamount of unlabeled data. The performance of these semi-supervised methodssignificantly degrades as the size of labeled data decreases. We introduceMutual-information-based Unsupervised & Semi-supervised Concurrent LEarning(MUSCLE), a hybrid learning approach that uses mutual information to combineboth unsupervised and semi-supervised learning. MUSCLE can be used as astand-alone training scheme for neural networks, and can also be incorporatedinto other learning approaches. We show that the proposed hybrid modeloutperforms state of the art on several standard benchmarks, includingCIFAR-10, CIFAR-100, and Mini-Imagenet. Furthermore, the performance gainconsistently increases with the reduction in the amount of labeled data, aswell as in the presence of bias. We also show that MUSCLE has the potential toboost the classification performance when used in the fine-tuning phase for amodel pre-trained only on unlabeled data.

MUSCLE: Strengthening Semi-Supervised Learning Via Concurrent Unsupervised Learning Using Mutual Information Maximization