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

The next generation of aircraft collision avoidance systems frame the problemas a Markov decision process and use dynamic programming to optimize thealerting logic. The resulting system uses a large lookup table to determineadvisories given to pilots, but these tables can grow very large. To enable thesystem to operate on limited hardware, prior work investigated compressing thetable using a deep neural network. However, ensuring that the neural networkreliably issues safe advisories is important for certification. This workdefines linearized regions where each advisory can be safely provided, allowingReluplex, a neural network verification tool, to check if unsafe advisories areever issued. A notional collision avoidance policy is generated and used totrain a neural network representation. The neural networks are checked forunsafe advisories, resulting in the discovery of thousands of unsafecounterexamples.

Verifying Aircraft Collision Avoidance Neural Networks Through Linear Approximations of Safe Regions