Information theoretic covariance complexity and its relation to pattern recognition

From MaRDI portal





In this paper, the author utilizes the discrimination information of a set of stochastic vectors to define a measure of the information theoretic complexity of the associated covariance matrix. He develops bounds that relate the covariance complexity to the maximum distance b between the characteristic roots of the covariance. Finally, a computationally efficient algorithm is proposed for finding the elements of a diagonal operator for minimizing the covariance complexity when the covariance is of the Toeplitz form.











This page was built for publication: Information theoretic covariance complexity and its relation to pattern recognition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3704714)