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

Labeling each instance in a large dataset is extremely labor- and time-consuming . One way to alleviate this problem is active learning, which aims towhich discover the most valuable instances for labeling to construct a powerfulclassifier. Considering both informativeness and representativeness provides apromising way to design a practical active learning. However, most existingactive learning methods select instances favoring either informativeness orrepresentativeness. Meanwhile, many are designed based on the binary class, sothat they may present suboptimal solutions on the datasets with multipleclasses. In this paper, a hybrid informative and representative criterion basedmulti-class active learning approach is proposed. We combine the informativeinformativeness and representativeness into one formula, which can be solvedunder a unified framework. The informativeness is measured by the marginminimum while the representative information is measured by the maximum meandiscrepancy. By minimizing the upper bound for the true risk, we generalize theempirical risk minimization principle to the active learning setting.Simultaneously, our proposed method makes full use of the label information,and the proposed active learning is designed based on multiple classes. So theproposed method is not suitable to the binary class but also the multipleclasses. We conduct our experiments on twelve benchmark UCI data sets, and theexperimental results demonstrate that the proposed method performs better thansome state-of-the-art methods.

Multi-class Active Learning: A Hybrid Informative and Representative Criterion Inspired Approach