%0 Conference Proceedings
%T Measures of Model Interpretability for Model Selection
%+ System Design Engineering (SYDE)
%+ School of Public Health and Health Systems [Waterloo]
%A Carrington, André
%A Fieguth, Paul
%A Chen, Helen
%Z Part 5: MAKE Explainable AI
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 2nd International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE)
%C Hamburg, Germany
%Y Andreas Holzinger
%Y Peter Kieseberg
%Y A Min Tjoa
%Y Edgar Weippl
%I Springer International Publishing
%3 Machine Learning and Knowledge Extraction
%V LNCS-11015
%P 329-349
%8 2018-08-27
%D 2018
%R 10.1007/978-3-319-99740-7_24
%K Model interpretability
%K Model transparency
%K Support vector machines
%K Kernels
%Z Computer Science [cs]
%Z Humanities and Social Sciences/Library and information sciencesConference papers
%X 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.
%G English
%Z TC 5
%Z TC 8
%Z TC 12
%Z WG 8.4
%Z WG 8.9
%Z WG 12.9
%2 https://inria.hal.science/hal-02060060/document
%2 https://inria.hal.science/hal-02060060/file/472936_1_En_24_Chapter.pdf
%L hal-02060060
%U https://inria.hal.science/hal-02060060
%~ SHS
%~ LORIA2
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-TC5
%~ IFIP-WG
%~ IFIP-TC12
%~ IFIP-TC8
%~ IFIP-WG8-4
%~ IFIP-WG8-9
%~ IFIP-CD-MAKE
%~ IFIP-WG12-9
%~ IFIP-LNCS-11015