LOCALLY IMPLEMENTABLE MATRIX FLOWS AND THEIR APPLICATION TO NEURAL NETWORK LEARNING
Jeroen Dehaene, Joos P. L. Vandewalle · Journal of Circuits Systems and Computers · 1994
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.