Formal Methods Meet Machine Learning (F3ML)

Kim G. Larsen; Axel Legay; Gerrit Nolte; Maximilian Schlüter; Mariëlle Stoelinga; Bernhard Steffen

doi:10.1007/978-3-031-19759-8_24

Formal Methods Meet Machine Learning (F3ML)

Kim G. Larsen, Axel Legay, Gerrit Nolte, Maximilian Schlüter^*, Mariëlle Stoelinga, Bernhard Steffen

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic

6 Citations (Scopus)

799 Downloads (Pure)

Abstract

The field of machine learning focuses on computationally efficient, yet approximate algorithms. On the contrary, the field of formal methods focuses on mathematical rigor and provable correctness. Despite their superficial differences, both fields offer mutual benefit. Formal methods offer methods to verify and explain machine learning systems, aiding their adoption in safety critical domains. Machine learning offers approximate, computationally efficient approaches that let formal methods scale to larger problems. This paper gives an introduction to the track “Formal Methods Meets Machine Learning” (F3ML) and shortly presents its scientific contributions, structured into two thematic subthemes: One, concerning formal methods based approaches for the explanation and verification of machine learning systems, and one concerning the employment of machine learning approaches to scale formal methods.

Original language	English
Title of host publication	Leveraging Applications of Formal Methods, Verification and Validation. Adaptation and Learning
Subtitle of host publication	11th International Symposium, ISoLA 2022, Rhodes, Greece, October 22-30, 2022, Proceedings, Part III
Editors	Tiziana Margaria, Bernhard Steffen
Place of Publication	Cham
Publisher	Springer Nature
Pages	393-405
Number of pages	13
ISBN (Electronic)	978-3-031-19759-8
ISBN (Print)	978-3-031-19758-1
DOIs	https://doi.org/10.1007/978-3-031-19759-8_24
Publication status	Published - 17 Oct 2022
Event	11th International Symposium on Leveraging Applications of Formal Methods, Verification and Validation, ISoLA 2022 - Rhodes, Greece Duration: 22 Oct 2022 → 30 Oct 2022 Conference number: 11

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	13703
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	11th International Symposium on Leveraging Applications of Formal Methods, Verification and Validation, ISoLA 2022
Abbreviated title	ISoLA 2022
Country/Territory	Greece
City	Rhodes
Period	22/10/22 → 30/10/22

Keywords

2023 OA procedure

Access to Document

10.1007/978-3-031-19759-8_24

ArticleFinal published version, 1.33 MBLicence: Taverne

Cite this

Larsen, K. G., Legay, A., Nolte, G., Schlüter, M., Stoelinga, M., & Steffen, B. (2022). Formal Methods Meet Machine Learning (F3ML). In T. Margaria, & B. Steffen (Eds.), Leveraging Applications of Formal Methods, Verification and Validation. Adaptation and Learning : 11th International Symposium, ISoLA 2022, Rhodes, Greece, October 22-30, 2022, Proceedings, Part III (pp. 393-405). (Lecture Notes in Computer Science; Vol. 13703). Springer Nature. https://doi.org/10.1007/978-3-031-19759-8_24

Larsen, Kim G. ; Legay, Axel ; Nolte, Gerrit et al. / Formal Methods Meet Machine Learning (F3ML). Leveraging Applications of Formal Methods, Verification and Validation. Adaptation and Learning : 11th International Symposium, ISoLA 2022, Rhodes, Greece, October 22-30, 2022, Proceedings, Part III. editor / Tiziana Margaria ; Bernhard Steffen. Cham : Springer Nature, 2022. pp. 393-405 (Lecture Notes in Computer Science).

@inproceedings{f83059bc09144b67be0156cab201fa8b,

title = "Formal Methods Meet Machine Learning (F3ML)",

abstract = "The field of machine learning focuses on computationally efficient, yet approximate algorithms. On the contrary, the field of formal methods focuses on mathematical rigor and provable correctness. Despite their superficial differences, both fields offer mutual benefit. Formal methods offer methods to verify and explain machine learning systems, aiding their adoption in safety critical domains. Machine learning offers approximate, computationally efficient approaches that let formal methods scale to larger problems. This paper gives an introduction to the track “Formal Methods Meets Machine Learning” (F3ML) and shortly presents its scientific contributions, structured into two thematic subthemes: One, concerning formal methods based approaches for the explanation and verification of machine learning systems, and one concerning the employment of machine learning approaches to scale formal methods.",

keywords = "2023 OA procedure",

author = "Larsen, {Kim G.} and Axel Legay and Gerrit Nolte and Maximilian Schl{\"u}ter and Mari{\"e}lle Stoelinga and Bernhard Steffen",

year = "2022",

month = oct,

day = "17",

doi = "10.1007/978-3-031-19759-8_24",

language = "English",

isbn = "978-3-031-19758-1",

series = "Lecture Notes in Computer Science",

publisher = "Springer Nature",

pages = "393--405",

editor = "Tiziana Margaria and Bernhard Steffen",

booktitle = "Leveraging Applications of Formal Methods, Verification and Validation. Adaptation and Learning",

address = "Switzerland",

note = "11th International Symposium on Leveraging Applications of Formal Methods, Verification and Validation, ISoLA 2022, ISoLA 2022 ; Conference date: 22-10-2022 Through 30-10-2022",

}

Larsen, KG, Legay, A, Nolte, G, Schlüter, M, Stoelinga, M & Steffen, B 2022, Formal Methods Meet Machine Learning (F3ML). in T Margaria & B Steffen (eds), Leveraging Applications of Formal Methods, Verification and Validation. Adaptation and Learning : 11th International Symposium, ISoLA 2022, Rhodes, Greece, October 22-30, 2022, Proceedings, Part III. Lecture Notes in Computer Science, vol. 13703, Springer Nature, Cham, pp. 393-405, 11th International Symposium on Leveraging Applications of Formal Methods, Verification and Validation, ISoLA 2022, Rhodes, Greece, 22/10/22. https://doi.org/10.1007/978-3-031-19759-8_24

Formal Methods Meet Machine Learning (F3ML). / Larsen, Kim G.; Legay, Axel; Nolte, Gerrit et al.
Leveraging Applications of Formal Methods, Verification and Validation. Adaptation and Learning : 11th International Symposium, ISoLA 2022, Rhodes, Greece, October 22-30, 2022, Proceedings, Part III. ed. / Tiziana Margaria; Bernhard Steffen. Cham: Springer Nature, 2022. p. 393-405 (Lecture Notes in Computer Science; Vol. 13703).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic

TY - GEN

T1 - Formal Methods Meet Machine Learning (F3ML)

AU - Larsen, Kim G.

AU - Legay, Axel

AU - Nolte, Gerrit

AU - Schlüter, Maximilian

AU - Stoelinga, Mariëlle

AU - Steffen, Bernhard

N1 - Conference code: 11

PY - 2022/10/17

Y1 - 2022/10/17

N2 - The field of machine learning focuses on computationally efficient, yet approximate algorithms. On the contrary, the field of formal methods focuses on mathematical rigor and provable correctness. Despite their superficial differences, both fields offer mutual benefit. Formal methods offer methods to verify and explain machine learning systems, aiding their adoption in safety critical domains. Machine learning offers approximate, computationally efficient approaches that let formal methods scale to larger problems. This paper gives an introduction to the track “Formal Methods Meets Machine Learning” (F3ML) and shortly presents its scientific contributions, structured into two thematic subthemes: One, concerning formal methods based approaches for the explanation and verification of machine learning systems, and one concerning the employment of machine learning approaches to scale formal methods.

AB - The field of machine learning focuses on computationally efficient, yet approximate algorithms. On the contrary, the field of formal methods focuses on mathematical rigor and provable correctness. Despite their superficial differences, both fields offer mutual benefit. Formal methods offer methods to verify and explain machine learning systems, aiding their adoption in safety critical domains. Machine learning offers approximate, computationally efficient approaches that let formal methods scale to larger problems. This paper gives an introduction to the track “Formal Methods Meets Machine Learning” (F3ML) and shortly presents its scientific contributions, structured into two thematic subthemes: One, concerning formal methods based approaches for the explanation and verification of machine learning systems, and one concerning the employment of machine learning approaches to scale formal methods.

KW - 2023 OA procedure

U2 - 10.1007/978-3-031-19759-8_24

DO - 10.1007/978-3-031-19759-8_24

M3 - Conference contribution

SN - 978-3-031-19758-1

T3 - Lecture Notes in Computer Science

SP - 393

EP - 405

BT - Leveraging Applications of Formal Methods, Verification and Validation. Adaptation and Learning

A2 - Margaria, Tiziana

A2 - Steffen, Bernhard

PB - Springer Nature

CY - Cham

T2 - 11th International Symposium on Leveraging Applications of Formal Methods, Verification and Validation, ISoLA 2022

Y2 - 22 October 2022 through 30 October 2022

ER -

Larsen KG, Legay A, Nolte G, Schlüter M, Stoelinga M, Steffen B. Formal Methods Meet Machine Learning (F3ML). In Margaria T, Steffen B, editors, Leveraging Applications of Formal Methods, Verification and Validation. Adaptation and Learning : 11th International Symposium, ISoLA 2022, Rhodes, Greece, October 22-30, 2022, Proceedings, Part III. Cham: Springer Nature. 2022. p. 393-405. (Lecture Notes in Computer Science). doi: 10.1007/978-3-031-19759-8_24

Formal Methods Meet Machine Learning (F3ML)

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this