Analytical Study of Neural Network Techniques: SOM, MLP and Classifier-A Survey

Abstract

This paper focuses on the various neural network techniques including Multilayer perceptron (MLP) neural network, classifier and self-organizing maps (SOMs). Various aspects of neural network techniques are mentioned in this paper along with the advantages and drawbacks. The neural network models are trained with measured values of the field strength at arbitrary points. The back propagation training algorithm is used for the learning process in MLP. The mechanism of supervised and unsupervised learning are also specified.