A hybrid approach of neural network and level-2 fuzzy set

Abstract

This paper presents a new high performance algorithm for the classification problems. The structure of A Hybrid Approach of Neural Network and Level-2 Fuzzy set, including two main processes. The first process of this structure is the learning algorithm. This step applied the combination of the multilayer perceptron neural network and the level-2 fuzzy set for learning. The outputs from learning process are fed to the classification process by using the K-nearest neighbor. The classification results on standard datasets show better accuracy than other high performance Neuro-Fuzzy methods.