Continuous verification of machine learning: A declarative programming approach

Ekaterina Komendantskaya; Wen Kokke; Daniel Kienitz

doi:10.1145/3414080.3414081

Continuous verification of machine learning: A declarative programming approach

Ekaterina Komendantskaya, Wen Kokke, Daniel Kienitz

HWU

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

2 Citations (Scopus)

Abstract

In this invited talk, we discuss state of the art in neural network verification. We propose the term continuous verification to characterise the family of methods that explore continuous nature of machine learning algorithms. We argue that methods of continuous verification must rely on robust programming language infrastructure (refinement types, automated proving, type-driven program synthesis), which provides a major opportunity for the declarative programming language community. Keywords: Neural Networks, Verification, AI.

Original language	English
Title of host publication	PPDP '20: Proceedings of the 22nd International Symposium on Principles and Practice of Declarative
Publisher	Association for Computing Machinery
ISBN (Electronic)	9781450388214
DOIs	https://doi.org/10.1145/3414080.3414081
Publication status	Published - Sept 2020
Event	22nd International Symposium on Principles and Practice of Declarative Programming 2020 - Bologna, Italy Duration: 8 Sept 2020 → 10 Sept 2020 Conference number: 22 http://www.cse.chalmers.se/~abela/ppdp20/

Conference

Conference	22nd International Symposium on Principles and Practice of Declarative Programming 2020
Abbreviated title	PPDP 2020
Country/Territory	Italy
City	Bologna
Period	8/09/20 → 10/09/20
Internet address	http://www.cse.chalmers.se/~abela/ppdp20/

ASJC Scopus subject areas

Human-Computer Interaction
Computer Networks and Communications
Computer Vision and Pattern Recognition
Software

Access to Document

10.1145/3414080.3414081

Cite this

@inproceedings{268db5bb85084a0ca555bb7950efa2b9,

title = "Continuous verification of machine learning: A declarative programming approach",

abstract = "In this invited talk, we discuss state of the art in neural network verification. We propose the term continuous verification to characterise the family of methods that explore continuous nature of machine learning algorithms. We argue that methods of continuous verification must rely on robust programming language infrastructure (refinement types, automated proving, type-driven program synthesis), which provides a major opportunity for the declarative programming language community. Keywords: Neural Networks, Verification, AI. ",

author = "Ekaterina Komendantskaya and Wen Kokke and Daniel Kienitz",

year = "2020",

month = sep,

doi = "10.1145/3414080.3414081",

language = "English",

booktitle = "PPDP '20: Proceedings of the 22nd International Symposium on Principles and Practice of Declarative",

publisher = "Association for Computing Machinery",

address = "United States",

note = "22nd International Symposium on Principles and Practice of Declarative Programming 2020, PPDP 2020 ; Conference date: 08-09-2020 Through 10-09-2020",

url = "http://www.cse.chalmers.se/~abela/ppdp20/",

}

Komendantskaya, E, Kokke, W & Kienitz, D 2020, Continuous verification of machine learning: A declarative programming approach. in PPDP '20: Proceedings of the 22nd International Symposium on Principles and Practice of Declarative., 1, Association for Computing Machinery, 22nd International Symposium on Principles and Practice of Declarative Programming 2020, Bologna, Italy, 8/09/20. https://doi.org/10.1145/3414080.3414081

Continuous verification of machine learning : A declarative programming approach. / Komendantskaya, Ekaterina; Kokke, Wen; Kienitz, Daniel.

PPDP '20: Proceedings of the 22nd International Symposium on Principles and Practice of Declarative. Association for Computing Machinery, 2020. 1.

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

TY - GEN

T1 - Continuous verification of machine learning

T2 - 22nd International Symposium on Principles and Practice of Declarative Programming 2020

AU - Komendantskaya, Ekaterina

AU - Kokke, Wen

AU - Kienitz, Daniel

N1 - Conference code: 22

PY - 2020/9

Y1 - 2020/9

N2 - In this invited talk, we discuss state of the art in neural network verification. We propose the term continuous verification to characterise the family of methods that explore continuous nature of machine learning algorithms. We argue that methods of continuous verification must rely on robust programming language infrastructure (refinement types, automated proving, type-driven program synthesis), which provides a major opportunity for the declarative programming language community. Keywords: Neural Networks, Verification, AI.

AB - In this invited talk, we discuss state of the art in neural network verification. We propose the term continuous verification to characterise the family of methods that explore continuous nature of machine learning algorithms. We argue that methods of continuous verification must rely on robust programming language infrastructure (refinement types, automated proving, type-driven program synthesis), which provides a major opportunity for the declarative programming language community. Keywords: Neural Networks, Verification, AI.

UR - http://www.scopus.com/inward/record.url?scp=85092789783&partnerID=8YFLogxK

U2 - 10.1145/3414080.3414081

DO - 10.1145/3414080.3414081

M3 - Conference contribution

AN - SCOPUS:85092789783

BT - PPDP '20: Proceedings of the 22nd International Symposium on Principles and Practice of Declarative

PB - Association for Computing Machinery

Y2 - 8 September 2020 through 10 September 2020

ER -

Continuous verification of machine learning: A declarative programming approach

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this