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

Several areas have been improved with Deep Learning during the past years.For non-safety related products adoption of AI and ML is not an issue, whereasin safety critical applications, robustness of such approaches is still anissue. A common challenge for Deep Neural Networks (DNN) occur when exposed toout-of-distribution samples that are previously unseen, where DNNs can yieldhigh confidence predictions despite no prior knowledge of the input.  In this paper we analyse two supervisors on two well-known DNNs with variedsetups of training and find that the outlier detection performance improveswith the quality of the training procedure. We analyse the performance of thesupervisor after each epoch during the training cycle, to investigatesupervisor performance as the accuracy converges. Understanding therelationship between training results and supervisor performance is valuable toimprove robustness of the model and indicates where more work has to be done tocreate generalized models for safety critical applications.

Performance Analysis of Out-of-Distribution Detection on Various Trained Neural Networks