Using Multi-layered Feed-forward Neural Network (MLFNN) Architecture as Bidirectional Associative Memory (BAM) for Function Approximation

Abstract

Function approximation is to find the underlying relationship from a given finite input-output data. It has numerous applications such as prediction, pattern recognition, data mining and classification etc. Multi- layered feed-forward neural networks (MLFNNs) with the use of back propagation algorithm have been extensively used for the purpose of function approximation recently. Another class of neural networks BAM has also been experimented for the same problem with lot of variations. In the present paper we have proposed the application of back propagation algorithm to MLFNN in such a way that it works like BAM and the result thus presented show greater and speedy approximation for the example function.