Performance Analysis of Artificial Neural Network Using Gray Related Analysis (GRA) Method

Abstract

Neural Network in GRA (Gray-related analysis). These types of gene regulatory networks. Of gene expression in this paper Artificial neural networks as a model of dynamics Networks we use networks. Other of the system Expression of genes by means of a gene Product the importance matrix of regulatory effect is defined. Positive and/or negative the model considers mutational regulation including feedback. Research significance: on the expression of a particular gene Regulatory effect as a neural network Based on the assumption that can be expressed a new model has been developed. Methology: Neural Network in GRA (Gray-related analysis) method Alternative: Neural Network, Training time, Execution time, Information content. Evaluation Preference: Back-scattering, counter scattering, Boltzmann Machine, Hopfield Network, BAM. Result: shows that from the result it is seen that BAM and is got the first rank whereas is the counter propagation got is having the lowest rank. Conclusion: The value of the dataset for Neural Network in GRA (Gray-related analysis) method shows that it results in BAM and top ranking.