Service interruption on Monday 11 July from 12:30 to 13:00: all the sites of the CCSD (HAL, EpiSciences, SciencesConf, AureHAL) will be inaccessible (network hardware connection).
Skip to Main content Skip to Navigation
Conference papers

Combining Data-Driven and Knowledge-Based AI Paradigms for Engineering AI-Based Safety-Critical Systems

Abstract : The development of AI-based systems entails a manifold of doubled-hard challenges. They are mainly due, on one side, to the technical debt of involved engineering disciplines (systems, safety, security), their inherent complexity, their yetto-solve concerns, and, on the other side, to the emergent risks of AI autonomy, the trade-offs between AI heuristics vs. required determinism, and, overall, the difficulty to define, characterize, assess and prove that AI-based systems are sufficiently safe and trustworthy. Despite the vast amount of research contributions and the undeniable progress in many fields over the last decades, a gap still exists between experimental and certifiable AIs. The present paper aims at bridging this gap "by design". Considering engineering paradigms as a basis to specify, relate and infer knowledge, a new paradigm is proposed to achieve AI certification. The proposed paradigm recognizes existing AI approaches, namely connectionist, symbolic, and hybrid, and proffers to leverage their essential traits captured as knowledge. A conceptual meta-body is thus obtained respectively containing categories for Data-, Knowledge-and Hybrid-driven. Since it is observed that research strays from Knowledge-driven and it rather strives for Data-driven approaches, our paradigm calls for empowering Knowledge Engineering relying upon Hybrid-driven approaches to improve their coupling and benefit from their complementarity.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03622260
Contributor : Juliette MATTIOLI Connect in order to contact the contributor
Submitted on : Monday, March 28, 2022 - 7:13:32 PM
Last modification on : Tuesday, May 3, 2022 - 11:32:37 AM
Long-term archiving on: : Wednesday, June 29, 2022 - 9:17:22 PM

File

SafeAI2022_Mattioli-Pedroza-Kh...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03622260, version 1

Citation

Juliette Mattioli, Gabriel Pedroza, Souhaiel Khalfaoui, Bertrand Leroy. Combining Data-Driven and Knowledge-Based AI Paradigms for Engineering AI-Based Safety-Critical Systems. Workshop on Artificial Intelligence Safety (SafeAI), Feb 2022, virtual, Canada. ⟨hal-03622260⟩

Share

Metrics

Record views

73

Files downloads

50