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

Improving the classification of multi-class imbalanced data is more difficultthan its two-class counterpart. In this paper, we use deep neural networks totrain new representations of tabular multi-class data. Unlike the typicallydeveloped re-sampling pre-processing methods, our proposal modifies thedistribution of features, i.e. the positions of examples in the learnedembedded representation, and it does not modify the class sizes. To learn suchembedded representations we introduced various definitions of triplet lossfunctions: the simplest one uses weights related to the degree of classimbalance, while the next proposals are intended for more complex distributionsof examples and aim to generate a safe neighborhood of minority examples.Similarly to the resampling approaches, after applying such preprocessing,different classifiers can be trained on new representations. Experiments withpopular multi-class imbalanced benchmark data sets and three classifiers showedthe advantage of the proposed approach over popular pre-processing methods aswell as basic versions of neural networks with classical loss functionformulations.

Deep Similarity Learning Loss Functions in Data Transformation for Class Imbalance