Toward Explainable Artificial Intelligence Through Fuzzy Systems

Alonso, José M.; Castiello, Ciro; Magdalena, Luis; Mencar, Corrado

doi:10.1007/978-3-030-71098-9_1

Cited by 10 publications

(2 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, there has been growing interest in using fuzzy logic to develop explanation methods [14]. The linguistic modeling and similarity to human reasoning make fuzzy logic [15] a useful formalism for providing explanations.…”

Section: Related Workmentioning

confidence: 99%

Multi-Class Fuzzy-LORE: A Method for Extracting Local and Counterfactual Explanations Using Fuzzy Decision Trees

et al. 2023

View full text Add to dashboard Cite

Multi-class classification is a fundamental task in Machine Learning. However, complex models can be viewed as black boxes, making it difficult to gain insight into how the model makes its predictions and build trust in its decision-making process. This paper presents a novel method called Multi-Class Fuzzy-LORE (mcFuzzy-LORE) for explaining the decisions made by multi-class fuzzy-based classifiers such as Fuzzy Random Forests (FRF). mcFuzzy-LORE is an adaptation of the Fuzzy-LORE method that uses fuzzy decision trees as an alternative to classical decision trees, providing interpretable, human-readable rules that describe the reasoning behind the model’s decision for a specific input. The proposed method was evaluated on a private dataset that was used to train an FRF-based multi-class classifier that assesses the risk of developing diabetic retinopathy in diabetic patients. The results show that mcFuzzy-LORE outperforms prior classical LORE-based methods in the generation of counterfactual instances.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-Class Fuzzy-LORE: A Method for Extracting Local and Counterfactual Explanations Using Fuzzy Decision Trees

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Therefore, it is important to develop advanced BAMSs that help in providing managers with valuable explanations about their BAMSs. It becomes challenging that BAMSs solve the trust issues with their managers/users by using explainable AI (XAI) tools [111,112], which makes the "black-box" ML models used in BAMSs more transparent [113].…”

Section: Explainable Aimentioning

confidence: 99%