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 learning models are known to be overconfident in their predictions onout of distribution inputs. There have been several pieces of work to addressthis issue, including a number of approaches for building Bayesian neuralnetworks, as well as closely related work on detection of out of distributionsamples. Recently, there has been work on building classifiers that are robustto out of distribution samples by adding a regularization term that maximizesthe entropy of the classifier output on out of distribution data. Toapproximate out of distribution samples (which are not known apriori), a GANwas used for generation of samples at the edges of the training distribution.In this paper, we introduce an alternative GAN based approach for building arobust classifier, where the idea is to use the GAN to explicitly generate outof distribution samples that the classifier is confident on (low entropy), andhave the classifier maximize the entropy for these samples. We showcase theeffectiveness of our approach relative to state-of-the-art on hand-writtencharacters as well as on a variety of natural image datasets.

Building robust classifiers through generation of confident out of distribution examples