Generalized canonical variate analysis of nonlinear systems

The canonical variate analysis (CVA) is extended to general nonlinear systems. Nonlinear canonical variables are shown to determine the optimum nonlinear transformation of the past maximizing the mutual information between the true and an approximating normal distribution. A sequential procedure for selection of the canonical variables is described. Nonlinear CVA is applied to nonlinear controlled Markov processes to obtain approximating nonlinear filters. A recursive innovations representation is given for the nonlinear filter that also yields an innovations representation for the Markov process model.<<ETX>>

[1]  A. A. Desrochers,et al.  Modeling of nonlinear discrete-time systems from input-output data , 1988, Autom..

[2]  W. Larimore.  Indentification of nonlinear systems using canonical variance analysis , 1987, 26th IEEE Conference on Decision and Control.

[3]  H. Akaike.  Canonical Correlation Analysis of Time Series and the Use of an Information Criterion , 1976 .

[4]  Solomon Kullback,et al.  Information Theory and Statistics , 1960 .

[5]  W. Larimore.  System Identification, Reduced-Order Filtering and Modeling via Canonical Variate Analysis , 1983, 1983 American Control Conference.

[6]  R. Brent,et al.  The Solution of Singular-Value and Symmetric Eigenvalue Problems on Multiprocessor Arrays , 1985 .

[7]  H. Hotelling.  Relations Between Two Sets of Variates , 1936 .

[8]  Franklin T. Luk,et al.  System Identification And Control Using SVD's On Systolic Arrays , 1988, Photonics West - Lasers and Applications in Science and Engineering.

[9]  A. Yaglom.  Outline of some topics in linear extrapolation of stationary random processes , 1967 .

[10]  H. Akaike.  Stochastic theory of minimal realization , 1974 .

[11]  Thomas Kailath,et al.  A view of three decades of linear filtering theory , 1974, IEEE Trans. Inf. Theory.

[12]  Victor J. Yohai,et al.  Canonical Variables as Optimal Predictors , 1980 .

[13]  Wallace E. Larimore,et al.  Predictive inference, sufficiency, entropy and an asymptotic likelihood principle , 1983 .

[14]  H. Akaike.  Markovian Representation of Stochastic Processes by Canonical Variables , 1975 .

[15]  C. Loan.  Generalizing the Singular Value Decomposition , 1976 .

[16]  M. Fliess,et al.  On the Approximation of Nonlinear Systems by Some Simple State-Space Models , 1982 .

[17]  Franklin T. Luk.  A parallel method for computing the generalized singular value decomposition , 1985, J. Parallel Distributed Comput..