A formal approach to explainability

Lior Wolf, Tomer Galanti, Tamir Hazan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We regard explanations as a blending of the input sample and the model's output and offer a few definitions that capture various desired properties of the function that generates these explanations. We study the links between these properties and between explanation-generating functions and intermediate representations of learned models and are able to show, for example, that if the activations of a given layer are consistent with an explanation, then so do all other subsequent layers. In addition, we study the intersection and union of explanations as a way to construct new explanations.

Original languageEnglish
Title of host publicationAIES 2019 - Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society
Pages255-261
Number of pages7
ISBN (Electronic)9781450363242
DOIs
StatePublished - 27 Jan 2019
Event2nd AAAI/ACM Conference on AI, Ethics, and Society, AIES 2019 - Honolulu, United States
Duration: 27 Jan 201928 Jan 2019

Publication series

NameAIES 2019 - Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society

Conference

Conference2nd AAAI/ACM Conference on AI, Ethics, and Society, AIES 2019
Country/TerritoryUnited States
CityHonolulu
Period27/01/1928/01/19

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'A formal approach to explainability'. Together they form a unique fingerprint.

Cite this