Certifiable Artificial Intelligence Through Data Fusion
Not on the map. Why?
Abstract (arXiv)
This paper reviews and proposes concerns in adopting, fielding, and maintaining artificial intelligence (AI) systems. While the AI community has made rapid progress, there are challenges in certifying AI systems. Using procedures from design and operational test and evaluation, there are opportunities towards determining performance bounds to manage expectations of intended use. A notional use case is presented with image data fusion to support AI object recognition certifiability considering precision versus distance.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 55 references that are in the map. First posted on arXiv 3 Nov 2021.
Builds on
9 of 55 references.
References · 9
- 2018Model Cards for Model Reportingcited by 1,080
- 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
- 2019Clustered Object Detection in Aerial Imagescited by 83
- 2016Towards Verified Artificial Intelligencecited by 36
- 2020VIFB: A Visible and Infrared Image Fusion Benchmarkcited by 25
- 2021Neural Network Verification in Controlcited by 14
- 2019Blockchain Methods for Trusted Avionics Systemscited by 3
- 2019Artificial Intelligence Strategies for National Security and Safety Standardscited by 3
- 2021Multisource AI Scorecard Table for System Evaluationcited by 3
Built on by
Not cited yet.