An Improved Gauss-Newtons Method based Back-propagation Algorithm for Fast Convergence

摘要

The present work deals with an improved back-propagation algorithm based onGauss-Newton numerical optimization method for fast convergence. The steepestdescent method is used for the back-propagation. The algorithm is tested usingvarious datasets and compared with the steepest descent back-propagationalgorithm. In the system, optimization is carried out using multilayer neuralnetwork. The efficacy of the proposed method is observed during the trainingperiod as it converges quickly for the dataset used in test. The requirement ofmemory for computing the steps of algorithm is also analyzed.