Uniform Approximation of Discrete-Space Multidimensional Myopic Maps

Our main result is a theorem that gives, in a certain setting, a necessary and sufficient condition under which discrete-space multidimensional shift-invariant input-output maps with vector-valued inputs drawn from a certain large set can be uniformly approximated arbitrarily well using a structure consisting of a linear preprocessing stage followed by a memoryless nonlinear network. Noncausal as well as causal maps are considered. Approximations for noncausal maps for which inputs and outputs are functions of more than one variable are of current interest in connection with, for example, image processing.

[1]  Leon O. Chua,et al.  Fading memory and the problem of approximating nonlinear operators with volterra series , 1985 .

[2]  I. Sandberg,et al.  A perspective on system theory , 1984 .

[3]  Hong Chen,et al.  Approximations of continuous functionals by neural networks with application to dynamic systems , 1993, IEEE Trans. Neural Networks.

[4]  I. W. Sandberg,et al.  Uniform approximation and the circle criterion , 1993, IEEE Trans. Autom. Control..

[5]  L. A. Li︠u︡sternik,et al.  Elements of Functional Analysis , 1962 .

[6]  W. Rudin.  Principles of mathematical analysis , 1964 .

[7]  J. Dieudonne.  Foundations of Modern Analysis , 1969 .

[8]  I. Sandberg,et al.  Network approximation of input-output maps and functionals , 1995, Proceedings of 1995 34th IEEE Conference on Decision and Control.

[9]  J.C. Principe,et al.  Adaline with adaptive recursive memory , 1991, Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop.

[10]  Irwin W. Sandberg,et al.  Uniform approximation of multidimensional myopic maps , 1997 .

[11]  C. Micchelli,et al.  Approximation by superposition of sigmoidal and radial basis functions , 1992 .

[12]  Hong Chen,et al.  Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems , 1995, IEEE Trans. Neural Networks.

[13]  I. Sandberg.  Approximately-finite memory and input-output maps , 1992, [Proceedings] 1992 IEEE International Symposium on Circuits and Systems.

[14]  Irwin W. Sandberg,et al.  Structure theorems for nonlinear systems , 1991, Multidimens. Syst. Signal Process..

[15]  M. Stone.  The Generalized Weierstrass Approximation Theorem , 1948 .

[16]  Jooyoung Park,et al.  Approximation and Radial-Basis-Function Networks , 1993, Neural Computation.

[17]  M. Schetzen.  The Volterra and Wiener Theories of Nonlinear Systems , 1980 .

[18]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[19]  Vito Volterra,et al.  Theory of Functionals and of Integral and Integro-Differential Equations , 2005 .