Publication
Architecture-independent approximation of functions
Journal Article (2001)
Journal
Neural Computation
Pages
1119-1135
Volume
13
Number
5
Doc link
http://dx.doi.org/10.1162/08997660151134352
File
Abstract
We show that minimizing the expected error of a feedforward network over a distribution of weights results in an approximation that tends to be independent of network size as the number of hidden units grows. This minimization can be easily performed, and the complexity of the resulting function implemented by the network is regulated by the variance of the weight distribution. For a fixed variance, there is a number of hidden units above which either the implemented function does not change or the change is slight and tends to zero as the size of the network grows. In sum, the control of the complexity depends on only the variance, not the architecture, provided it is large enough.
Categories
robots.
Author keywords
learning, function approximation, network size
Scientific reference
V. Ruiz de Angulo and C. Torras. Architecture-independent approximation of functions. Neural Computation, 13(5): 1119-1135, 2001.
Follow us!