Neural State Classification (NSC) [19] is a scalable method for the analysis of hybrid systems, which consists in learning a neural network-based classifier able to detect whether or not an unsafe state can be reached from a certain configuration of a hybrid system. NSC has very high accuracy, yet it is prone to prediction errors that can affect system safety. To overcome this limitation, we present a method, based on the theory of conformal prediction, that complements NSC predictions with statistically sound estimates of prediction uncertainty. This results in a principled criterion to reject potentially erroneous predictions a priori, i.e., without knowing the true reachability values. Our approach is highly efficient (with runtimes in the order of milliseconds) and effective, managing in our experiments to successfully reject almost all the wrong NSC predictions.

Conformal predictions for hybrid system state classification

Luca Bortolussi
;
Francesca Cairoli
;
2019

Abstract

Neural State Classification (NSC) [19] is a scalable method for the analysis of hybrid systems, which consists in learning a neural network-based classifier able to detect whether or not an unsafe state can be reached from a certain configuration of a hybrid system. NSC has very high accuracy, yet it is prone to prediction errors that can affect system safety. To overcome this limitation, we present a method, based on the theory of conformal prediction, that complements NSC predictions with statistically sound estimates of prediction uncertainty. This results in a principled criterion to reject potentially erroneous predictions a priori, i.e., without knowing the true reachability values. Our approach is highly efficient (with runtimes in the order of milliseconds) and effective, managing in our experiments to successfully reject almost all the wrong NSC predictions.
978-3-030-31514-6
File in questo prodotto:
File Dimensione Formato  
paper_7.pdf

embargo fino al 31/07/2020

Descrizione: The final publication is available at Springer via https://link.springer.com/chapter/10.1007/978-3-030-31514-6_13
Tipologia: Bozza finale post-referaggio (post-print)
Licenza: Copyright Editore
Dimensione 1.4 MB
Formato Adobe PDF
1.4 MB Adobe PDF Visualizza/Apri
Bortolussi, cover+index.pdf

non disponibili

Tipologia: Documento in Versione Editoriale
Licenza: Copyright Editore
Dimensione 1.58 MB
Formato Adobe PDF
1.58 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11368/2953918
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
social impact