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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper presents an approach for verifying the behaviour of nonlinearArtificial Neural Networks (ANNs) found in cyber-physical safety-criticalsystems. We implement a dedicated interval constraint propagator for thesigmoid function into the SMT solver iSAT and compare this approach with acompositional approach encoding the sigmoid function by basic arithmeticfeatures available in iSAT and an approximating approach. Our experimentalresults show that the dedicated and the compositional approach clearlyoutperform the approximating approach. Throughout all our benchmarks, thededicated approach showed an equal or better performance compared to thecompositional approach.

Verification of Sigmoidal Artificial Neural Networks using iSAT