Explainable AI: A Review of Machine Learning Interpretability Methods.

Linardatos P, Papastefanopoulos V, Kotsiantis S. · 2020

Read Explainable AI: A Review of Machine Learning Interpretability Methods. by Linardatos P, Papastefanopoulos V, Kotsiantis S. (2020) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc7824368.txt.

Introduction

Linardatos and co-authors review methods that make machine learning models explainable. AI systems now beat humans at many tasks. Their growing complexity turned them into black boxes. Users cannot see how a decision is reached. That opacity blocks use in touchy fields like health care.

Explainable AI aims to open the box. The authors survey the interpretability methods on offer. They sort the methods into a clear taxonomy. Links to working code implementations are included. Fairness and sensitivity concerns get their own treatment. The survey is meant as a reference for builders and theorists alike. Trust in automated decisions is the end goal.

Catalog record

CREATORLinardatos P, Papastefanopoulos V, Kotsiantis S.
YEAR2020
COLLECTIONPAPERS
FORMATTXT
FILE SIZE154 KB
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC7824368

Browse the full library · About the Tower of Babel