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/

Zendy Plus

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

Zendy Tools

Zendy Open

Deep Neural Networks, often owing to the overparameterization, are shown tobe capable of exactly memorizing even randomly labelled data. Empirical studieshave also shown that none of the standard regularization techniques mitigatesuch overfitting. We investigate whether the choice of the loss function canaffect this memorization. We empirically show, with benchmark data sets MNISTand CIFAR-10, that a symmetric loss function, as opposed to eithercross-entropy or squared error loss, results in significant improvement in theability of the network to resist such overfitting. We then provide a formaldefinition for robustness to memorization and provide a theoretical explanationas to why the symmetric losses provide this robustness. Our results clearlybring out the role loss functions alone can play in this phenomenon ofmemorization.

Memorization in Deep Neural Networks: Does the Loss Function matter?