Title :
A modified backpropagation algorithm
Author :
Verma, Bipin Kumar ; Mulawka, J.J.
Author_Institution :
Dept. of Fundamental Electron., Warsaw Univ. of Technol.
fDate :
27 Jun-2 Jul 1994
Abstract :
A long and uncertain training process is one of the most important problems for a multilayer neural network using the backpropagation algorithm. In this paper, a modified backpropagation algorithm for a certain and fast training process is presented. The modification is based on the solving of the weight matrix for the output layer using theory of equations and least squares techniques
Keywords :
backpropagation; multilayer perceptrons; least squares techniques; modified backpropagation algorithm; multilayer neural network; output layer; training process; weight matrix; Backpropagation algorithms; Equations; Least squares methods; Multi-layer neural network; Neural networks; Neurons;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374289
