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

Deep neural networks have demonstrated state-of-the-art performance on manyclassification tasks. However, they have no inherent capability to recognizewhen their predictions are wrong. There have been several efforts in the recentpast to detect natural errors but the suggested mechanisms pose additionalenergy requirements. To address this issue, we propose an ensemble ofclassifiers at hidden layers to enable energy efficient detection of naturalerrors. In particular, we append Relevant-features based Auxiliary Cells (RACs)which are class specific binary linear classifiers trained on relevantfeatures. The consensus of RACs is used to detect natural errors. Based oncombined confidence of RACs, classification can be terminated early, therebyresulting in energy efficient detection. We demonstrate the effectiveness ofour technique on various image classification datasets such as CIFAR-10,CIFAR-100 and Tiny-ImageNet.

Relevant-features based Auxiliary Cells for Energy Efficient Detection of Natural Errors