The University of Southampton
University of Southampton Institutional Repository

Neural networks in imandra: matrix representation as a verification choice

Neural networks in imandra: matrix representation as a verification choice
Neural networks in imandra: matrix representation as a verification choice

The demand for formal verification tools for neural networks has increased as neural networks have been deployed in a growing number of safety-critical applications. Matrices are a data structure essential to formalising neural networks. Functional programming languages encourage diverse approaches to matrix definitions. This feature has already been successfully exploited in different applications. The question we ask is whether, and how, these ideas can be applied in neural network verification. A functional programming language Imandra combines the syntax of a functional programming language and the power of an automated theorem prover. Using these two key features of Imandra, we explore how different implementations of matrices can influence automation of neural network verification.

Formal verification, Functional programming, Imandra, Matrices, Neural networks
0302-9743
78-95
Springer Cham
Desmartin, Remi
77bb429f-d009-496e-bf29-067c5f9f775a
Passmore, Grant
e949128f-abca-4acc-87be-a9fd6a7a5f41
Kommendentskaya, Ekaterina
f12d9c23-5589-40b8-bcf9-a04fe9dedf61
Isac, Omri
Katz, Guy
Ivanov, Radoslav
Narodytska, Nina
Nenzi, Laura
Desmartin, Remi
77bb429f-d009-496e-bf29-067c5f9f775a
Passmore, Grant
e949128f-abca-4acc-87be-a9fd6a7a5f41
Kommendentskaya, Ekaterina
f12d9c23-5589-40b8-bcf9-a04fe9dedf61
Isac, Omri
Katz, Guy
Ivanov, Radoslav
Narodytska, Nina
Nenzi, Laura

Desmartin, Remi, Passmore, Grant and Kommendentskaya, Ekaterina (2022) Neural networks in imandra: matrix representation as a verification choice. Isac, Omri, Katz, Guy, Ivanov, Radoslav, Narodytska, Nina and Nenzi, Laura (eds.) In Software Verification and Formal Methods for ML-Enabled Autonomous Systems - 5th International Workshop, FoMLAS 2022, and 15th International Workshop, NSV 2022, Proceedings. vol. 13466 LNCS, Springer Cham. pp. 78-95 . (doi:10.1007/978-3-031-21222-2_6).

Record type: Conference or Workshop Item (Paper)

Abstract

The demand for formal verification tools for neural networks has increased as neural networks have been deployed in a growing number of safety-critical applications. Matrices are a data structure essential to formalising neural networks. Functional programming languages encourage diverse approaches to matrix definitions. This feature has already been successfully exploited in different applications. The question we ask is whether, and how, these ideas can be applied in neural network verification. A functional programming language Imandra combines the syntax of a functional programming language and the power of an automated theorem prover. Using these two key features of Imandra, we explore how different implementations of matrices can influence automation of neural network verification.

This record has no associated files available for download.

More information

Published date: 16 December 2022
Additional Information: Funding Information: E. Komendantskaya—Acknowledges support of EPSRC grant EP/T026952/1. Publisher Copyright: © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Venue - Dates: 5th International Workshop on Software Verification and Formal Methods for ML-Enables Autonomous Systems, FoMLAS 2022 and 15th International Workshop on Numerical Software Verification, NSV 2022, , Haifa, Israel, 2022-08-11 - 2022-08-11
Keywords: Formal verification, Functional programming, Imandra, Matrices, Neural networks

Identifiers

Local EPrints ID: 482743
URI: http://eprints.soton.ac.uk/id/eprint/482743
ISSN: 0302-9743
PURE UUID: c8464a0b-45a3-4407-9a6f-fb6006303496

Catalogue record

Date deposited: 12 Oct 2023 16:39
Last modified: 05 Jun 2024 19:30

Export record

Altmetrics

Contributors

Author: Remi Desmartin
Author: Grant Passmore
Author: Ekaterina Kommendentskaya
Editor: Omri Isac
Editor: Guy Katz
Editor: Radoslav Ivanov
Editor: Nina Narodytska
Editor: Laura Nenzi

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×