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

The $F_\beta$ score is a commonly used measure of classification performance,which plays crucial roles in classification tasks with imbalanced data sets.However, the $F_\beta$ score cannot be used as a loss function bygradient-based learning algorithms for optimizing neural network parameters dueto its non-differentiability. On the other hand, commonly used loss functionssuch as the binary cross-entropy (BCE) loss are not directly related toperformance measures such as the $F_\beta$ score, so that neural networksoptimized by using the loss functions may not yield optimal performancemeasures. In this study, we investigate a relationship between classificationperformance measures and loss functions in terms of the gradients with respectto the model parameters. Then, we propose a differentiable surrogate lossfunction for the optimization of the $F_\beta$ score. We show that the gradientpaths of the proposed surrogate $F_\beta$ loss function approximate thegradient paths of the large sample limit of the $F_\beta$ score. Throughnumerical experiments using ResNets and benchmark image data sets, it isdemonstrated that the proposed surrogate $F_\beta$ loss function is effectivefor optimizing $F_\beta$ scores under class imbalances in binary classificationtasks compared with other loss functions.

A surrogate loss function for optimization of $F_\beta$ score in binary classification with imbalanced data