Performance Analysis For Multilayer Feed Forward Neural Network With Grad-ient Descent with Momentum & Adaptive Back Prop-agation and Bfgs QuasiNew-ton Back Propagation for Hand Written Hindi Characters of Swars
Abstract
This paper analyzes the performance of multi layer feed foward Neural Networks with Gradient descent with momentum and adaptive back propagation (TRAINGDX) and BFGS quasi-Newton back propagation (TRAINBFG) for hand written Hindi Characters of SWARS. In this analysis, five hand written Hindi characters of SWARS from different people are collected and stored as an image. The MATLAB function is used to determine the densities of these scanned images after partitioning the image into 16 portions. These 16 densities for each character are used as an input pattern for the two different Neural Network architec-tures. The two learning rules as the variant of Back Propagation learning algorithm are used to train these Neural Networks. The performance of these two Neural Networks are analyzed for convergence and trends of error in the case of non conver-gence. There are some interesting and important observations which have been considered for trends of error in the case of non convergence. The inheritance of local minima Problem of back propagation algorithm massively affects these two proposed learning algorithm also.
Authors
Rajesh Lavania , Manu Pratap Singh