Clustered-Hybrid Multilayer Perceptron network for pattern recognition application

摘要: This paper introduces a modified version of the Hybrid Multilayer Perceptron (HMLP) network to improve performance conventional HMLP network. We adopted Clustering Algorithm from Radial Basis Function (RBF) architecture and incorporated it into architecture. The model is called Clustered-Hybrid (Clustered-HMLP) proposed Clustered-HMLP trained using training algorithm Clustered-Modified Recursive Prediction Error (Clustered-MRPE). capability with Clustered-MRPE demonstrated seven benchmark datasets University California at Irvine (UCI) machine learning repository (i.e. Iris, Ionosphere, Pima Indian Diabetes, Wine, Lung Cancer, Hayes-Roth Glass) compared other twelve classifiers reported in literature. Further, new implemented Transformer Fault Diagnosis System Aggregate Shape Identification System. results indicate that outperforms eleven provides significant improvement for pattern recognition application.