Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Hoitsma, Fabian"'
In this paper, we integrate the concepts of feature importance with implicit bias in the context of pattern classification. This is done by means of a three-step methodology that involves (i) building a classifier and tuning its hyperparameters, (ii)
Externí odkaz:
http://arxiv.org/abs/2305.09399
Autor:
Nápoles, Gonzalo, Hoitsma, Fabian, Knoben, Andreas, Jastrzebska, Agnieszka, Espinosa, Maikel Leon
This paper presents a Prolog-based reasoning module to generate counterfactual explanations given the predictions computed by a black-box classifier. The proposed symbolic reasoning module can also resolve what-if queries using the ground-truth label
Externí odkaz:
http://arxiv.org/abs/2112.12641
Autor:
Nápoles, Gonzalo, Hoitsma, Fabian, Knoben, Andreas, Jastrzebska, Agnieszka, Leon Espinosa, Maikel
Publikováno v:
In Information Sciences April 2023 622:1196-1227
