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 loss function is arguably among the most important hyperparameters for aneural network. Many loss functions have been designed to date, making acorrect choice nontrivial. However, elaborate justifications regarding thechoice of the loss function are not made in related work. This is, as we seeit, an indication of a dogmatic mindset in the deep learning community whichlacks empirical foundation. In this work, we consider deep neural networks in asupervised classification setting and analyze the impact the choice of lossfunction has onto the training result. While certain loss functions performsuboptimally, our work empirically shows that under-represented losses such asthe KL Divergence can outperform the State-of-the-Art choices significantly,highlighting the need to include the loss function as a tuned hyperparameterrather than a fixed choice.

Evaluating the Impact of Loss Function Variation in Deep Learning for Classification