IROF: a low resource evaluation metric for explanation methods

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

8 Downloads (Pure)

Abstract

The adoption of machine learning in health care hinges on the transparency of the used algorithms, necessitating the need for explanation methods. However, despite a growing literature on explaining neural networks, no consensus has been reached on how to evaluate those explanation methods. We propose IROF, a new approach to evaluating explanation methods that circumvents the need for manual evaluation. Compared to other recent work, our approach requires several orders of magnitude less computational resources and no human input, making it accessible to lower resource groups and robust to human bias.
Original languageEnglish
Title of host publicationProceedings of the Workshop AI for Affordable Healthcare at ICLR 2020
Number of pages11
Publication date2020
Publication statusPublished - 2020
EventWorkshop AI for Affordable Healthcare at ICLR 2020 - Virtual event, Addis Ababa, Ethiopia
Duration: 26 Apr 202026 Apr 2020

Workshop

WorkshopWorkshop AI for Affordable Healthcare at ICLR 2020
LocationVirtual event
CountryEthiopia
CityAddis Ababa
Period26/04/202026/04/2020

Fingerprint Dive into the research topics of 'IROF: a low resource evaluation metric for explanation methods'. Together they form a unique fingerprint.

Cite this