Our research aims to propose a new performance-explainability analytical framework to assess and benchmark machine learning methods. The framework details a set of characteristics that systematize the performance-explainability assessment of existing machine learning methods. In order to illustrate the use of the framework, we apply it to benchmark the current state-of-the-art multivariate time series classifiers.
@article{arxiv.2005.14501,
title = {A Performance-Explainability Framework to Benchmark Machine Learning Methods: Application to Multivariate Time Series Classifiers},
author = {Kevin Fauvel and Véronique Masson and Élisa Fromont},
journal= {arXiv preprint arXiv:2005.14501},
year = {2021}
}
Comments
In Proceedings of the IJCAI-PRICAI 2020 Workshop on Explainable Artificial Intelligence. An example of this framework in use is available in arXiv:2005.03645