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

Discriminatively trained, deterministic neural networks are the de factochoice for classification problems. However, even though they achievestate-of-the-art results on in-domain test sets, they tend to be overconfidenton out-of-distribution (OOD) data. For instance, ReLU networks -- a popularclass of neural network architectures -- have been shown to almost always yieldhigh confidence predictions when the test data are far away from the trainingset, even when they are trained with OOD data. We overcome this problem byadding a term to the output of the neural network that corresponds to the logitof an extra class, that we design to dominate the logits of the originalclasses as we move away from the training data.This technique provably preventsarbitrarily high confidence on far-away test data while maintaining a simplediscriminative point-estimate training. Evaluation on various benchmarksdemonstrates strong performance against competitive baselines on both far-awayand realistic OOD data.

Preventing Arbitrarily High Confidence on Far-Away Data in Point-Estimated Discriminative Neural Networks