Feasibility of random basis function approximators for modeling and control
Neural and Evolutionary Computing
2009-05-06 v1 Artificial Intelligence
Abstract
We discuss the role of random basis function approximators in modeling and control. We analyze the published work on random basis function approximators and demonstrate that their favorable error rate of convergence O(1/n) is guaranteed only with very substantial computational resources. We also discuss implications of our analysis for applications of neural networks in modeling and control.
Keywords
Cite
@article{arxiv.0905.0677,
title = {Feasibility of random basis function approximators for modeling and control},
author = {Ivan Tyukin and Danil Prokhorov},
journal= {arXiv preprint arXiv:0905.0677},
year = {2009}
}