Tensor product neural networks and approximation of dynamical systems
- 24 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 353-356
- https://doi.org/10.1109/iscas.1996.541606
Abstract
We consider the problem of approximating any member of a large class of input-output operators of nonlinear dynamical systems. The systems need not be shift invariant, and the system inputs need not be continuous. We introduce a family of "tensor product" dynamical neural networks, and show that a certain continuity condition is necessary and sufficient for the existence of arbitrarily good approximations using this family.Keywords
This publication has 4 references indexed in Scilit:
- General structures for classificationIEEE Transactions on Circuits and Systems I: Regular Papers, 1994
- Multivariate Approximation TheoryPublished by Society for Industrial & Applied Mathematics (SIAM) ,1986
- On the general theory of fading memoryArchive for Rational Mechanics and Analysis, 1968
- On the Boundedness of Solutions of Nonlinear Integral EquationsBell System Technical Journal, 1965