On the comparisons between two outer-supervised learning algorithms for finding the inversion of arbitrary nonsingular matrix

Abstract

This paper discusses using two kinds of outer-supervised learning algorithms, i.e., the constrained learning algorithm and recursive least squares algorithm, for finding the inversion of arbitrary nonsingular matrix (including the complex ones). We present the details of two kinds of outer-supervised learning algorithms respectively in this paper, and how to use them based on linear feedforward neural networks for finding the inversion of the arbitrary nonsingular matrix. Finally, to compare the corresponding performance for two learning methods, several simulation results are reported and discussed.