Learning Fuzzy Rule-Based Neural Networks for Control

Abstract

A three-step method for function approximation with a fuzzy sys(cid:173) tem is proposed. First, the membership functions and an initial rule representation are learned; second, the rules are compressed as much as possible using information theory; and finally, a com(cid:173) putational network is constructed to compute the function value. This system is applied to two control examples: learning the truck and trailer backer-upper control system, and learning a cruise con(cid:173) trol system for a radio-controlled model car.

Cite

Text

Higgins and Goodman. "Learning Fuzzy Rule-Based Neural Networks for Control." Neural Information Processing Systems, 1992.

Markdown

[Higgins and Goodman. "Learning Fuzzy Rule-Based Neural Networks for Control." Neural Information Processing Systems, 1992.](https://mlanthology.org/neurips/1992/higgins1992neurips-learning/)

BibTeX

@inproceedings{higgins1992neurips-learning,
  title     = {{Learning Fuzzy Rule-Based Neural Networks for Control}},
  author    = {Higgins, Charles M. and Goodman, Rodney M.},
  booktitle = {Neural Information Processing Systems},
  year      = {1992},
  pages     = {350-357},
  url       = {https://mlanthology.org/neurips/1992/higgins1992neurips-learning/}
}