Important Gene Selection Based on Gene Expression using Hopfield Network

Gene selection is an important issue in analyzing multiclass micro array data. Those genes which help sample classification are selected from the original set of genes and the redundant gene expression data are eliminated. In this paper the important genes are selected by updating the weights & by minimizing the error. The minimizations of errors are done by Hopfield network consisting of four perceptron model or modules. A dataset was taken as input and is multiplied by some random weights to get the output. This process continues in an iterative way until the error is minimized.  Based on these minimal errors, the best gene expression from the dataset is selected.