Rule Extraction with Guaranteed Fidelity - Artificial Intelligence Applications and Innovations (AIAI 2014 - Workshops:CoPA,MHDW, IIVC, and MT4BD) Access content directly
Conference Papers Year : 2014

Rule Extraction with Guaranteed Fidelity

Ulf Johansson
  • Function : Author
  • PersonId : 992372
Rikard König
  • Function : Author
  • PersonId : 992380
Henrik Linusson
  • Function : Author
  • PersonId : 992371
Tuve Löfström
  • Function : Author
  • PersonId : 992374
Henrik Boström
  • Function : Author
  • PersonId : 992373

Abstract

This paper extends the conformal prediction framework to rule extraction, making it possible to extract interpretable models from opaque models in a setting where either the infidelity or the error rate is bounded by a predefined significance level. Experimental results on 27 publicly available data sets show that all three setups evaluated produced valid and rather efficient conformal predictors. The implication is that augmenting rule extraction with conformal prediction allows extraction of models where test set errors or test sets infidelities are guaranteed to be lower than a chosen acceptable level. Clearly this is beneficial for both typical rule extraction scenarios, i.e., either when the purpose is to explain an existing opaque model, or when it is to build a predictive model that must be interpretable.
Fichier principal
Vignette du fichier
978-3-662-44722-2_30_Chapter.pdf (238 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01391055 , version 1 (02-11-2016)

Licence

Attribution

Identifiers

Cite

Ulf Johansson, Rikard König, Henrik Linusson, Tuve Löfström, Henrik Boström. Rule Extraction with Guaranteed Fidelity. 10th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2014, Rhodes, Greece. pp.281-290, ⟨10.1007/978-3-662-44722-2_30⟩. ⟨hal-01391055⟩
86 View
173 Download

Altmetric

Share

Gmail Facebook X LinkedIn More