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

Training convolutional neural networks for image classification tasks usuallycauses information loss. Although most of the time the information lost isredundant with respect to the target task, there are still cases wherediscriminative information is also discarded. For example, if the samples thatbelong to the same category have multiple correlated features, the model mayonly learn a subset of the features and ignore the rest. This may not be aproblem unless the classification in the test set highly depends on the ignoredfeatures. We argue that the discard of the correlated discriminativeinformation is partially caused by the fact that the minimization of theclassification loss doesn't ensure to learn the overall discriminativeinformation but only the most discriminative information. To address thisproblem, we propose an information flow maximization (IFM) loss as aregularization term to find the discriminative correlated features. With lessinformation loss the classifier can make predictions based on more informativefeatures. We validate our method on the shiftedMNIST dataset and show theeffectiveness of IFM loss in learning representative and discriminativefeatures.

Learning to Find Correlated Features by Maximizing Information Flow in Convolutional Neural Networks