We present the design of a meta-programming system for hybrid AI, integrating spatial model checking and machine learning. The proposed system architecture blends together different programming languages and execution technologies using a simplified, declarative meta-language. The design features a global-model-checking-alike execution model, backed up by a microservices architecture. The system is meant to be a follow up to the spatial model checker VoxLogicA currently used for research on declarative medical image analysis, aimed at explainable by construction artificial intelligence.
Towards hybrid-AI in imaging using VoxLogicA
Bussi L.;Ciancia V.;Latella D.;Massink M.
2024
Abstract
We present the design of a meta-programming system for hybrid AI, integrating spatial model checking and machine learning. The proposed system architecture blends together different programming languages and execution technologies using a simplified, declarative meta-language. The design features a global-model-checking-alike execution model, backed up by a microservices architecture. The system is meant to be a follow up to the spatial model checker VoxLogicA currently used for research on declarative medical image analysis, aimed at explainable by construction artificial intelligence.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
978-3-031-75387-9_13.pdf
solo utenti autorizzati
Descrizione: Towards Hybrid-AI in Imaging Using VoxLogicA
Tipologia:
Versione Editoriale (PDF)
Licenza:
NON PUBBLICO - Accesso privato/ristretto
Dimensione
607.19 kB
Formato
Adobe PDF
|
607.19 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
|
ISoLA24.pdf
accesso aperto
Descrizione: This is the Submitted version (preprint) of the following paper: Belmonte G. et al., “Towards Hybrid-AI in Imaging using VoxLogicA”, 2024, submitted to “ISoLA 2024 - 12th International Symposium. Leveraging Applications of Formal Methods, Verification and Validation. Software Engineering Methodologies”. The final published version is available on the publisher’s website https://doi.org/10.1007/978-3-031-75387-9_13.
Tipologia:
Documento in Pre-print
Licenza:
Altro tipo di licenza
Dimensione
615.65 kB
Formato
Adobe PDF
|
615.65 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
