The past decade has witnessed wide applications of deep neural networks in anomaly detection. However, the dearth interpretability often hinders their reliability, especially for industrial where practical users heavily rely on interpretable methods to provide explanations decision-making. In this paper, we propose a reconstruction-based approach unsupervised detection anomalies defect data. Ou...

A miracle happens In one hand we have a class of marvelously complex theories in predicate logic theories with su cient coding potential like PA Peano Arithmetic or ZF Zermelo Fraenkel Set Theory In the other we have certain modal propositional theories of striking simplicity We translate the modal operators of the modal theories to certain speci c xed de ned predicates of the predicate logical...

This paper presents work using crowdsourcing to assess explanations for supervised text classification. In this paper, an explanation is defined to be a set of words from the input text that a classifier or human believes to be most useful for making a classification decision. We compared two types of explanations for classification decisions: human-generated and computer-generated. The compari...

Article history: Available online 4 March 2011

System modeling with fuzzy rule-based systems (FRBSs), i.e. fuzzy modeling (FM), usually comes with two contradictory requirements in the obtained model: the interpretability, capability to express the behavior of the real system in an understandable way, and the accuracy, capability to faithfully represent the real system. While linguistic FM (mainly developed by linguistic FRBSs) is focused o...

Human-robot interactive decision-making is increasingly becoming ubiquitous, and trust an influential factor in determining the reliance on autonomy. However, it not reasonable to systems that are beyond our comprehension, typical machine learning data-driven black-box paradigms impede interpretability. Therefore, critical establish computational trustworthy mechanisms enhanced by interpretabil...

In this paper we turn the attention to a well developed theory of fuzzy/lin-guis-tic models that are interpretable and, moreover, can be learned from the data.We present four different situations demonstrating both interpretability as well as learning abilities of these models.

Neuro-fuzzy classi cation systems make it possible to obtain a suitable fuzzy classi er by learning from data. Nevertheless, in some cases the derived rule base is hard to interpret. In this paper we discuss some approaches to improve the interpretability of neuro-fuzzy classi cation systems. We present modi ed learning strategies to derive fuzzy classi cation rules from data, and some methods ...