## Abstract Radial basis functions are of interest in connection with a variety of approximation problems in the neural networks area, and in other areas as well. Here we show that the members of some interesting families of shiftβvarying inputβoutput maps, that take a function space into a functio
Network approximation of input-output maps and functionals
β Scribed by Irwin W. Sandberg; Lilian Xu
- Book ID
- 112495139
- Publisher
- Springer
- Year
- 1996
- Tongue
- English
- Weight
- 666 KB
- Volume
- 15
- Category
- Article
- ISSN
- 0278-081X
No coin nor oath required. For personal study only.
π SIMILAR VOLUMES
We consider multidimensional shift-invariant input-output maps G from a relatively compact set of functions S to a set of real-valued functions, and we give criteria under which these maps can be uniformly approximated arbitrarily well using a certain structure consisting of a not-necessarily linear
A body of results is given concerning the character of the response of systems represented by discrete-time approximately-"nite-memory input}output maps G with input and outputs de"ned on +0, 1, 2 ,. Conditions are given under which, for example, the system's output approaches a limit as kPR wheneve