Witold Pedrycz

TL;DR: The key point of this study is to reduce the computational complexity of type-2 fuzzy set-based models and to alleviate the deterioration of its generalization abilities through the synergistic effect of two algorithms: first, intervaltype-2 FCM is used in the hidden layer of the network and connections (weights) are adjusted by invoking the least squares error estimation method.

TL;DR: In this article , several generalized evidential divergences (EDs) are proposed and studied to measure the difference and discrepancy between basic belief assignments (BBAs) in DSE theory, which have more universal applicability in decision theory.

TL;DR: Point Instance Network (PINet) as mentioned in this paper is a traffic line detection method based on the key points estimation and instance segmentation approach, which includes several hourglass models that are trained simultaneously with the same loss function.

TL;DR: A detailed comparative analysis carried out from the viewpoint of the performance and the design methodology, is provided for the fuzzy cascade controller and the conventional PD cascade controller whose design relied on the use of the serial genetic algorithms.

TL;DR: This study introduces a concept of Self-organizing neurofuzzy networks (SONFN), a hybrid modeling architecture combining neurofuzzle networks (NFN) and polynomial neural networks (PNN) and discusses two classes of SONFN architectures and proposes comprehensive learning algorithms.