Understanding Neural Networks

Abstract

Neural Networks have seen an explosion of interest over the last few years. The primary appeal of neural networks is their ability to emulate the brain's pattern recognition skills. The sweeping success of neural networks can be attributed to some key factors. This paper explains the architecture of neural networks and also enlightens how neural networks are being successfully applied an extraordinary range of problem domain [1]. Neural Networks (NN) are important data mining tools used for classification and clustering. It is an attempt to build machines that will mimic brain activities and be able to learn. Neural Networks usually learn by examples. If NN is supplied with enough examples, it should be able to perform classification and even discover new trends or patterns in data. Basic NN is composed of three layers, input, output, and hidden layers. Each layer can have number of nodes and nodes from input layers are connected to the nodes from hidden layer. Nodes from hidden layers are connected to the nodes from output layer. Those connections represent weights between nodes [2].