LOCALLY IMPLEMENTABLE MATRIX FLOWS AND THEIR APPLICATION TO NEURAL NETWORK LEARNING
1994 ◽
Vol 04
(01)
◽
pp. 23-51
◽
Keyword(s):
A number of matrix flows, based on isospectral and isodirectional flows, is studied and modified for the purpose of local implementability on a network structure. The flows converge to matrices with a predefined spectrum and eigenvectors which are determined by an external signal. The flows can be useful for adaptive signal processing applications and are applied to neural network learning.
Keyword(s):
Keyword(s):
2010 ◽
Vol 54
(1-2)
◽
pp. 59
Keyword(s):
2011 ◽
Vol 131
(11)
◽
pp. 1889-1894
2018 ◽
Vol 06
(01)
◽
pp. 32-36
1992 ◽