ML Anthology

Improving the Generalization Properties of Radial Basis Function Neural Networks

Chris Bishop
NeCo 1991 pp. 579-588
doi:10.1162/NECO.1991.3.4.579 /neco/1991/bishop1991neco-improving/

Abstract

An important feature of radial basis function neural networks is the existence of a fast, linear learning algorithm in a network capable of representing complex nonlinear mappings. Satisfactory generalization in these networks requires that the network mapping be sufficiently smooth. We show that a modification to the error functional allows smoothing to be introduced explicitly without significantly affecting the speed of training. A simple example is used to demonstrate the resulting improvement in the generalization properties of the network.

NeCo Semantic Scholar

Cite

Text

Bishop. "Improving the Generalization Properties of Radial Basis Function Neural Networks." Neural Computation, 1991. doi:10.1162/NECO.1991.3.4.579

Markdown

[Bishop. "Improving the Generalization Properties of Radial Basis Function Neural Networks." Neural Computation, 1991.](https://mlanthology.org/neco/1991/bishop1991neco-improving/) doi:10.1162/NECO.1991.3.4.579

BibTeX

@article{bishop1991neco-improving,
  title     = {{Improving the Generalization Properties of Radial Basis Function Neural Networks}},
  author    = {Bishop, Chris},
  journal   = {Neural Computation},
  year      = {1991},
  pages     = {579-588},
  doi       = {10.1162/NECO.1991.3.4.579},
  volume    = {3},
  url       = {https://mlanthology.org/neco/1991/bishop1991neco-improving/}
}