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

Despite the unresolved 'dying ReLU problem', the classical ReLU activationfunction (AF) has been extensively applied in Deep Neural Networks (DNN), inparticular Convolutional Neural Networks (CNN), for image classification. Thecommon gradient issues of ReLU pose challenges in applications on academy andindustry sectors. Recent approaches for improvements are in a similar directionby just proposing variations of the AF, such as Leaky ReLU (LReLU), whilemaintaining the solution within the same unresolved gradient problems. In thispaper, the Absolute Leaky ReLU (ALReLU) AF, a variation of LReLU, is proposed,as an alternative method to resolve the common 'dying ReLU problem' on NN-basedalgorithms for supervised learning. The experimental results demonstrate thatby using the absolute values of LReLU's small negative gradient, has asignificant improvement in comparison with LReLU and ReLU, on imageclassification of diseases such as COVID-19, text and tabular dataclassification tasks on five different datasets.

ALReLU: A different approach on Leaky ReLU activation function to improve Neural Networks Performance