Networks and the best approximation property (Q751636): Difference between revisions
From MaRDI portal
Added link to MaRDI item. |
Removed claims |
||
Property / author | |||
Property / author: Federico Girosi / rank | |||
Property / author | |||
Property / author: Tomaso Poggio / rank | |||
Revision as of 19:45, 11 February 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Networks and the best approximation property |
scientific article |
Statements
Networks and the best approximation property (English)
0 references
1990
0 references
Networks can be considered as approximation schemes. It is well known that multilayer networks of the perceptron type can approximate arbitrarily well continuous functions. A similar result is proven for networks derived from regularization theory and including radial basis functions. From the point of view of approximation theory, however, the property of approximating continuous functions arbitrarily well is not sufficient for characterizing good approximation schemes. More critical is the property of best approximation, that is the presence of an element of minimum distance from the function that has to be approximated. In this paper it is shown that multilayer perceptron networks, of the type used in backpropagation, do not have this property. For regularization networks (in particular radial basis function networks) existence and uniqueness of best approximation immediately derives from the linearity of the theory.
0 references
approximation schemes
0 references
multilayer networks
0 references
regularization theory
0 references
radial basis functions
0 references
best approximation
0 references
multilayer perceptron
0 references