ANN modeling for the prediction of elastic moduli of ternary glass systems using physicochemical properties of the oxide components

Abstract Artificial neural network (ANN) consists of an interconnected group of neurons which process the information. ANN can be used as a non-linear statistical data modeling tool. Due to their inherent adaptive nature they learn by example while training and acquire intelligence to capture the non-linear and complex relationships between the inputs and outputs. In this study a multilayer perception (MLP) feed forward neural network has been developed for predicting the elastic moduli of ternary oxide glass systems using the physicochemical properties of the oxide components.