The level of strength of an explanation: A quantitative evaluation technique for post-hoc XAI methods
Authors:
- Marilyn BelloMBMarilyn Bello
- Rosalís AmadorRARosalís Amador
- María-Matilde GarcíaMGMaría-Matilde García
- Javier Del SerJavier Del Ser
- Pablo MesejoPablo Mesejo
- Óscar CordónÓCÓscar Cordón
- 29 November 2024
- journal article
- research article
- Published by Elsevier in Pattern Recognition
- Vol. 161
Abstract
No abstract availableKeywords
This publication has 24 references indexed in Scilit:
- REPROT: Explaining the predictions of complex deep learning architectures for object detection through reducts of an imageInformation Sciences, 2023
- Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial IntelligenceInformation Fusion, 2023
- Visual explanation of black-box model: Similarity Difference and Uniqueness (SIDU) methodPattern Recognition, 2022
- Checklist for responsible deep learning modeling of medical images based on COVID-19 detection studiesPattern Recognition, 2021
- Levels of explainable artificial intelligence for human-aligned conversational explanationsArtificial Intelligence, 2021
- Using ontologies to enhance human understandability of global post-hoc explanations of black-box modelsArtificial Intelligence, 2021
- Methods for interpreting and understanding deep neural networksDigital Signal Processing, 2018
- A guideline for the validation of likelihood ratio methods used for forensic evidence evaluationForensic Science International, 2017
- Likelihood ratio data to report the validation of a forensic fingerprint evaluation methodData in Brief, 2017
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015