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

Robustness in deep neural networks and machine learning algorithms in generalis an open research challenge. In particular, it is difficult to ensurealgorithmic performance is maintained on out-of-distribution inputs oranomalous instances that cannot be anticipated at training time. Embodiedagents will be deployed in these conditions, and are likely to make incorrectpredictions. An agent will be viewed as untrustworthy unless it can maintainits performance in dynamic environments. Most robust training techniques aim toimprove model accuracy on perturbed inputs; as an alternate form of robustness,we aim to reduce the severity of mistakes made by neural networks inchallenging conditions. We leverage current adversarial training methods togenerate targeted adversarial attacks during the training process in order toincrease the semantic similarity between a model's predictions and true labelsof misclassified instances. Results demonstrate that our approach performsbetter with respect to mistake severity compared to standard and adversariallytrained models. We also find an intriguing role that non-robust features playwith regards to semantic similarity.

Addressing Mistake Severity in Neural Networks with Semantic Knowledge