Summary: Presented in III Congresso Brasileiro de Redes Neurais, Florianpo­
lis, SC, Julho, 1997, pp. 7--11.
A New Training Algorithm to Reduce the Computational
Complexity of Principal Component Analysis by Hebbian
Learning \Lambda
Maria Cristina Felippetto De Castro
cristina@ee.pucrs.br
Fernando C'esar C. De Castro
decastro@ee.pucrs.br
Jos'e Nelson Amaral
amaral@ee.pucrs.br
Paulo Roberto G. Franco
pfranco@ee.pucrs.br
Electrical Engineering Department
Pontif'icia Universidade Cat'olica do Rio Grande do Sul
90619­900 ­ Porto Alegre ­ RS ­ Brazil
Abstract
In this work we propose a technique that reduces
the computational complexity of training an Ar­
tificial Neural Network (ANN) through Hebbian

Source: Amaral, José Nelson - Department of Computing Science, University of Alberta

Collections: Computer Technologies and Information Sciences