Fast learning process of multilayer neural networks using recursive least squares method Azimi-Sadjadi, Mahmood R. ; Liou, Ren-Jean In this correspondence a new approach for the learning process of multilayer perceptron neural networks using the recursive least squares (RLS) type algorithm is proposed. This method minimizes the global sum of the squared errors between the actual and the desired output values iteratively. The weights in the network are updated upon the arrival-of a new training sample and by solving a system of normal equations recursively. To determine the desired target in the hidden layers an analog of backpropagation (BP) strategy used in the conventional learning algorithms is developed. This permits the application of the learning procedure to all the layers. Simulation results on the 4-b parity checker and multiplexer networks are obtained which indicate significant reduction in the total number of iterations when compared with those of the conventional and accelerated backpropagation (ABP) algorithms. Colorado State University. Libraries 1992 text ; image application/pdf ECEmra00034.pdf FACFECEN100514ARTI eng c1992 IEEE
Fast learning process of multilayer neural networks using recursive least squares method
Azimi-Sadjadi, Mahmood R. ; Liou, Ren-Jean
In this correspondence a new approach for the learning process of multilayer perceptron neural networks using the recursive least squares (RLS) type algorithm is proposed. This method minimizes the global sum of the squared errors between the actual and the desired output values iteratively. The weights in the network are updated upon the arrival-of a new training sample and by solving a system of normal equations recursively. To determine the desired target in the hidden layers an analog of backpropagation (BP) strategy used in the conventional learning algorithms is developed. This permits the application of the learning procedure to all the layers. Simulation results on the 4-b parity checker and multiplexer networks are obtained which indicate significant reduction in the total number of iterations when compared with those of the conventional and accelerated backpropagation (ABP) algorithms.
Colorado State University. Libraries
1992
text ; image
application/pdf
ECEmra00034.pdf
FACFECEN100514ARTI
eng
c1992 IEEE