A new training algorithm is presented as a faster alternative to the backpropagation method. The newc approach is based on the solution of a linear system at each step of the learning phase. The squared error of the output of each layer before the nonlinearity is minimized on the entire set of the learning patterns by a block LS algorithm. The optimal weights for each layer are then computed using the SVD technique. The simulation results have shown considerable improvements from the points of view of both the accuracy and the speed of convergence.
LS-backpropagation algorithm for training multilayer perceptrons / DI CLAUDIO, Elio; Parisi, Raffaele; Orlandi, Gianni. - STAMPA. - (1993), pp. 208-211. (Intervento presentato al convegno VI Italian Workshop on Neural Networks tenutosi a Vietri - SA, Italy nel 12-14 May 1993).
LS-backpropagation algorithm for training multilayer perceptrons
DI CLAUDIO, Elio;PARISI, Raffaele;ORLANDI, Gianni
1993
Abstract
A new training algorithm is presented as a faster alternative to the backpropagation method. The newc approach is based on the solution of a linear system at each step of the learning phase. The squared error of the output of each layer before the nonlinearity is minimized on the entire set of the learning patterns by a block LS algorithm. The optimal weights for each layer are then computed using the SVD technique. The simulation results have shown considerable improvements from the points of view of both the accuracy and the speed of convergence.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
