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

Test, Evaluation, Verification, and Validation (TEVV) for ArtificialIntelligence (AI) is a challenge that threatens to limit the economic andsocietal rewards that AI researchers have devoted themselves to producing. Acentral task of TEVV for AI is estimating brittleness, where brittlenessimplies that the system functions well within some bounds and poorly outside ofthose bounds. This paper argues that neither of those criteria are certain ofDeep Neural Networks. First, highly touted AI successes (eg. imageclassification and speech recognition) are orders of magnitude morefailure-prone than are typically certified in critical systems even withindesign bounds (perfectly in-distribution sampling). Second, performance fallsoff only gradually as inputs become further Out-Of-Distribution (OOD). Enhancedemphasis is needed on designing systems that are resilient despitefailure-prone AI components as well as on evaluating and improving OODperformance in order to get AI to where it can clear the challenging hurdles ofTEVV and certification.

Estimating the Brittleness of AI: Safety Integrity Levels and the Need for Testing Out-Of-Distribution Performance