The best approximation to C/sup 2/ functions and its error bounds using regular-center Gaussian networks

@article{Liu1994TheBA,
  title={The best approximation to C/sup 2/ functions and its error bounds using regular-center Gaussian networks},
  author={Binfan Liu and Jennie Si},
  journal={Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94)},
  year={1994},
  volume={4},
  pages={2400-2406 vol.4}
}
Gaussian neural networks are considered to approximate any C/sup 2/ function with support on the unit hypercube I/sub m/=[0,1]/sup m/ in the sense of best approximation. An upper bound (0(N/sup -2/)) of the approximation error is obtained in the present paper for a Gaussian network having N/sup m/ hidden neurons with centers defined on a regular mesh in I/sub m/.<<ETX>> 

Citations

Publications citing this paper.
SHOWING 1-10 OF 12 CITATIONS

Robust fuzzy control of nonlinear systems using shape-adaptive radial basis functions

  • Fuzzy Sets and Systems
  • 2002
VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Bayesian Signal Classifier

  • 2007 International Joint Conference on Neural Networks
  • 2007

Driver-Adaptive Assist System for Avoiding Abnormality in Driving

  • 2007 IEEE International Conference on Control Applications
  • 2007
VIEW 1 EXCERPT
CITES METHODS

Signal Self Organizing Map

  • 2007 International Joint Conference on Neural Networks
  • 2007

Neural Networks-Based Adaptive State Feedback Control of Robot Manipulators

  • TENCON 2006 - 2006 IEEE Region 10 Conference
  • 2006
VIEW 2 EXCERPTS
CITES BACKGROUND

An approach to tune fuzzy controllers based on reinforcement learning for autonomous vehicle control

  • IEEE Transactions on Intelligent Transportation Systems
  • 2005
VIEW 1 EXCERPT
CITES METHODS