Measures of Model Interpretability for Model Selection - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2018

Measures of Model Interpretability for Model Selection

André Carrington
  • Function : Author
  • PersonId : 1043707
Paul Fieguth
  • Function : Author
  • PersonId : 1043708


The literature lacks definitions for quantitative measures of model interpretability for automatic model selection to achieve high accuracy and interpretability, hence we define inherent model interpretability. We extend the work of Lipton et al. and Liu et al. from qualitative and subjective concepts of model interpretability to objective criteria and quantitative measures. We also develop another new measure called simplicity of sensitivity and illustrate prior, initial and posterior measurement. Measures are tested and validated with some measures recommended for use. It is demonstrated that high accuracy and high interpretability are jointly achievable with little to no sacrifice in either.
Fichier principal
Vignette du fichier
472936_1_En_24_Chapter.pdf (957.12 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02060060 , version 1 (07-03-2019)





André Carrington, Paul Fieguth, Helen Chen. Measures of Model Interpretability for Model Selection. 2nd International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE), Aug 2018, Hamburg, Germany. pp.329-349, ⟨10.1007/978-3-319-99740-7_24⟩. ⟨hal-02060060⟩
56 View
108 Download



Gmail Facebook X LinkedIn More