training procedure; data stream; computational intelligence; adaptive neuro-fuzzy system; extended neo-fuzzy neuron; membership function

This research contribution instantiates a framework of a hybrid cascade neural network rest on the application of a specific sort of neo-fuzzy elements and a new peculiar adaptive training rule. The main trait of the offered system is its competence to continue intensifying its cascades until the required accuracy is gained. A distinctive rapid training procedure is also covered in this case that gives the possibility to operate with nonstationary data streams in an attempt to provide online training of multiple parametric variables. A new training criterion is examined which suits for handling nonstationary objects. Added to everything else, there's always an occasion to set up (increase) an inference order and a quantity of membership relations inside the extended neo-fuzzy neuron.