Metric_Tools_for_Sensitivity_Analysis.pdf (11.01 MB)
Download file

Metric Tools for Sensitivity Analysis with Applications to Neural Networks

Download (11.01 MB)
posted on 2023-04-26, 03:58 authored by Jaime Pizarroso-GonzaloJaime Pizarroso-Gonzalo, David Alfaya, José Portela, Antonio Muñoz

In this paper, a theoretical framework is proposed to study sensitivities of Machine Learning models using metric techniques. From this metric interpretation, a complete family of new quantitative metrics called  α-curves is extracted. These  α-curves provide information with greater depth on the importance of the input variables for a machine learning model than existing XAI methods in the literature.  We demonstrate the effectiveness of the  α-curves using synthetic and real datasets, comparing the results against other XAI methods for variable importance and validating the analysis results with the ground truth or literature information. 


PID2019-108936GB- C21


Email Address of Submitting Author

ORCID of Submitting Author


Submitting Author's Institution

Pontifical Comillas University

Submitting Author's Country

  • Spain