Interpretability of linguistic fuzzy rule-based systems: An overview of interpretability measures

By María José Gacto, Rafael Alcalá, Francisco Herrera. Information Sciences, 2011

547 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/2c04bc1b7c91af0d3dc58afe24f8f5f2381f5423

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

Citations in the corpus

Evolutionary Fuzzy Systems for Explainable Artificial Intelligence: Why, When, What for, and Where to? (2019, background): “The practitioner will therefore be able to directly pair the necessary interpretability constraints while generating a model with a high predictive power [30], [31].”
A historical review of evolutionary learning methods for Mamdani-type fuzzy rule-based systems: Designing interpretable genetic fuzzy systems (2011, unknown): “Hence, the definition of more complex and plausible interpretability indexes has become a hot topic in the fuzzy modeling community in the last few years and some proposals have been made [16, 17, 74, 121, 168] with the aim of solving the latter problem.”
Explainable Artificial Intelligence: a Systematic Review (2020, background): “The former includes quantitative measures which consist of mathematical entities such as, for example, the size of models [26, 89, 319, 320, 269].”
Hybrid Decision Making: When Interpretable Models Collaborate With Black-Box Models (2018, methodology): “eﬁnitions of interpretability for rulebased models, such as the number of rules (Dash et al.,2018; Wang et al.,2017;Lakkaraju et al.,2016;Wang,2018), the number of conditions, and those discussed in (Gacto et al., 2011). The deﬁnition of interpretability is domain speciﬁc and subject to applications”
Trustworthy Artificial Intelligence: A Review (2022, methodology): “In-modeling approaches work well with less complicated model families like decision trees [153], linear models [173], and rule-based models [71].”
Comparison-Based Inverse Classification for Interpretability in Machine Learning (2018, methodology): “Although many numerical criteria for interpretability have been proposed (see e.g. [9]), there is no consensus about a global measure for the quality of an explanation.”