Engineering Dependable AI Systems

Adedjouma, Morayo; Alix, Christophe; Cantat, Loic; Jenn, Éric; Mattioli, Juliette; Robert, Boris; Tschirhart, Fabien; Voirin, Jean‐Luc

doi:10.1109/sose55472.2022.9812672

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Modeling will help ensure that all methods are compatible with each other, providing a consistent end-to-end process for designing reliable AI systems. The overall structure of the analysis framework [2] is depicted on fig. 2.…”

Section: Ai Specifics To Be Consideredmentioning

confidence: 99%

AI Engineering to Deploy Reliable AI in Industry

Mattioli,

Roux,

Braunschweig

et al. 2023

2023 Fifth International Conference on Transdisciplinary AI (TransAI)

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract

Section: Ai Specifics To Be Consideredmentioning

confidence: 99%

AI Engineering to Deploy Reliable AI in Industry

Mattioli,

Roux,

Braunschweig

et al. 2023

2023 Fifth International Conference on Transdisciplinary AI (TransAI)

View full text Add to dashboard Cite

show abstract

“…Various tools supporting the creation of ACs exist [15], such as ASCE [5], ISCaDE [6], Astah GSN [7], from Confiance.ai [8], or safeTbox [9], which are mainly designed to support safety engineers in assuring system-level safety. With these tools, ACs can be created from scratch in a flexible manner for a specific system.…”

Section: Background and Related Work On Assurance Casesmentioning

confidence: 99%

Operationalizing Assurance Cases for Data Scientists: A Showcase of Concepts and Tooling in the Context of Test Data Quality for Machine Learning

Jöckel,

Kläs,

Groß

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Assurance Cases (ACs) are an established approach in safety engineering to argue quality claims in a structured way. In the context of quality assurance for Machine Learning (ML)-based software components, ACs are also being discussed and appear promising. Tools for operationalizing ACs do exist, yet mainly focus on supporting safety engineers on the system level. However, assuring the quality of an ML component within the system is commonly the responsibility of data scientists, who are usually less familiar with these tools. To address this gap, we propose a framework to support the operationalization of ACs for ML components based on technologies that data scientists use on a daily basis: Python and Jupyter Notebook. Our aim is to make the process of creating ML-related evidence in ACs more effective. Results from the application of the framework, documented through notebooks, can be integrated into existing AC tools. We illustrate the application of the framework on an example excerpt concerned with the quality of the test data.

show abstract

Engineering Dependable AI Systems

Cited by 2 publications

References 0 publications

AI Engineering to Deploy Reliable AI in Industry

AI Engineering to Deploy Reliable AI in Industry

Operationalizing Assurance Cases for Data Scientists: A Showcase of Concepts and Tooling in the Context of Test Data Quality for Machine Learning

Contact Info

Product

Resources

About