The concept of window neuron, having a window-shaped activation function, is introduced. An appropriate learning rule, based on the solution of linear equations, is presented. Some simulation results show the efficiency and the generalization ability of neural networks obtained with this technique.
Training window neurons through the solution of linear equations
M Muselli
1992
Abstract
The concept of window neuron, having a window-shaped activation function, is introduced. An appropriate learning rule, based on the solution of linear equations, is presented. Some simulation results show the efficiency and the generalization ability of neural networks obtained with this technique.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
