On the Relationship between Generalization Error, Hypothesis Complexity, and Sample Complexity for Radial Basis Functions

Authors:
Partha Niyogi;Federico Girosi
Affiliations:
-;-
Venue:
On the Relationship between Generalization Error, Hypothesis Complexity, and Sample Complexity for Radial Basis Functions
Year:
1994

Citing 0
Cited 4

Online learning in radial basis function networks

Neural Computation
Sample Complexity for Function Learning Tasks through Linear Neural Networks

MICAI '02 Proceedings of the Second Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence
On the relationship between generalization error, hypothesis complexity, and sample complexity for radial basis functions

Neural Computation
Knowledge transfer using bayesian belief network

NN'06 Proceedings of the 7th WSEAS International Conference on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we bound the generalization error of a class of Radial Basis Function networks, for certain well defined function learning tasks, in terms of the number of parameters and number of examples. We show that the total generalization error is partly due to the insufficient representational capacity of the network (because of its finite size) and partly due to insufficient information about the target function (because of finite number of samples). We make several observations about generalization error which are valid irrespective of the approximation scheme. Our result also sheds light on ways to choose an appropriate network architecture for a particular problem.