What and How of Machine Learning Transparency: Building Bespoke Explainability Tools with Interoperable Algorithmic Components

Jupyter Notebook Python Submitted 09 April 2022 • Published 06 December 2022
Software repository Paper review Download paper Software archive
Review

Editor: @ttimbers (all papers)
Reviewers: @kvarada (all reviews), @arokem (all reviews)

Authors

Kacper Sokol (0000-0002-9869-5896), Alexander Hepburn (0000-0002-2674-1478), Raul Santos-Rodriguez (0000-0001-9576-3905), Peter Flach (0000-0001-6857-5810)

Citation

Sokol et al., (2022). What and How of Machine Learning Transparency: Building Bespoke Explainability Tools with Interoperable Algorithmic Components. Journal of Open Source Education, 5(58), 175, https://doi.org/10.21105/jose.00175

@article{Sokol2022, doi = {10.21105/jose.00175}, url = {https://doi.org/10.21105/jose.00175}, year = {2022}, publisher = {The Open Journal}, volume = {5}, number = {58}, pages = {175}, author = {Kacper Sokol and Alexander Hepburn and Raul Santos-Rodriguez and Peter Flach}, title = {What and How of Machine Learning Transparency: Building Bespoke Explainability Tools with Interoperable Algorithmic Components }, journal = {Journal of Open Source Education} }
Copy citation string · Copy BibTeX  
Tags

Transparency Explainability Interpretability Surrogate Explainers Tabular Data Artificial Intelligence Machine Learning Hands-on Tutorial

Altmetrics
Markdown badge

 

License

Authors of JOSE papers retain copyright.

This work is licensed under a Creative Commons Attribution 4.0 International License.

Creative Commons License

Journal of Open Source Education is an affiliate of the Open Source Inititative.

Journal of Open Source Education is part of Open Journals, which is a NumFOCUS-sponsored project.

Table of Contents
Public user content licensed CC BY 4.0 unless otherwise specified.
ISSN 2577-3569