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

We study the problem of safety verification of direct perception neuralnetworks, where camera images are used as inputs to produce high-level featuresfor autonomous vehicles to make control decisions. Formal verification ofdirect perception neural networks is extremely challenging, as it is difficultto formulate the specification that requires characterizing input asconstraints, while the number of neurons in such a network can reach millions.We approach the specification problem by learning an input propertycharacterizer which carefully extends a direct perception neural network atclose-to-output layers, and address the scalability problem by a novelassume-guarantee based verification approach. The presented workflow is used tounderstand a direct perception neural network (developed by Audi) whichcomputes the next waypoint and orientation for autonomous vehicles to follow.

Towards Safety Verification of Direct Perception Neural Networks