Fuzzy rule dropout with dynamic compensation for wide learning algorithm of TSK fuzzy classifier

Document Type


Publication Date



This paper extends our recent work about dropout for the design of Takagi–Sugeno–Kang(TSK) fuzzy classifiers, i.e., fuzzy-knowledge-out, to the generalized concept, i.e., fuzzy rule dropout with dynamic compensation. This extension is motivated by very complicated firing patterns of all pieces of knowledge in human brain, i.e., binary or continuous or both random ways for different situations. Our theoretical analysis indicates that this generalized concept can encapsulate various random dropouts of fuzzy rules with more match of human cognitive behavior, more capabilities of both generalization and co-adaptation avoidance. Based on this concept, we develop a wide learning algorithm of a TSK fuzzy classifier. Experimental results about the thirteen datasets demonstrate that with high interpretability guarantee, TSK fuzzy classifiers designed by means of fuzzy rule dropout with dynamic compensation outperform the comparative methods, especially in the sense of testing accuracy.

Publication Title

Applied Soft Computing



This document is currently not available here.