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

Advances in the field of Machine Learning and Deep Neural Networks (DNNs) hasenabled rapid development of sophisticated and autonomous systems. However, theinherent complexity to rigorously assure the safe operation of such systemshinders their real-world adoption in safety-critical domains such as aerospaceand medical devices. Hence, there is a surge in interest to explore the use ofadvanced mathematical techniques such as formal methods to address thischallenge. In fact, the initial results of such efforts are promising. Alongthese lines, we propose the use of quantifier elimination (QE) - a formalmethod technique, as a complimentary technique to the state-of-the-art staticanalysis and verification procedures. Using an airborne collision avoidance DNNas a case example, we illustrate the use of QE to formulate the precise rangeforward propagation through a network as well as analyze its robustness. Wediscuss the initial results of this ongoing work and explore the futurepossibilities of extending this approach and/or integrating it with otherapproaches to perform advanced safety assurance of DNNs.

Using Quantifier Elimination to Enhance the Safety Assurance of Deep Neural Networks