Performance Evaluation of Error Back Propagation Algorithm for Non-Linear Classification and Function Approximation in VHDL Platform
Implementation of error back propagation algorithm is carried out in VHDL platform for the purpose of in depth analysis of the effects of learning parameters on the accuracy and speed of convergence. In this paper, the authors present the implementation of Error Back Propagation Training algorithm (EBPT) in VHSIC Hardware Descriptive Language (VHDL) platform for two standard benchmark problems of nonlinear classification of XOR function and sine wave generation. The effect of variation of learning parameters on accuracy of the output and speed of convergence of the algorithm are presented. Improved speed of convergence without much change in accuracy was obtained by incorporating momentum method.