Continuous verification of machine learning: A declarative programming approach

Ekaterina Komendantskaya, Wen Kokke, Daniel Kienitz

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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 languageEnglish
Title of host publicationPPDP '20: Proceedings of the 22nd International Symposium on Principles and Practice of Declarative
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450388214
DOIs
Publication statusPublished - Sep 2020
Event22nd International Symposium on Principles and Practice of Declarative Programming 2020 - Bologna, Italy
Duration: 8 Sep 202010 Sep 2020
Conference number: 22
http://www.cse.chalmers.se/~abela/ppdp20/

Conference

Conference22nd International Symposium on Principles and Practice of Declarative Programming 2020
Abbreviated titlePPDP 2020
CountryItaly
CityBologna
Period8/09/2010/09/20
Internet address

ASJC Scopus subject areas

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

Fingerprint Dive into the research topics of 'Continuous verification of machine learning: A declarative programming approach'. Together they form a unique fingerprint.

Cite this