Fast Learning in Multi-Resolution Hierarchies

  title={Fast Learning in Multi-Resolution Hierarchies},
  author={John E. Moody},
A class of fast, supervised learning algorithms is presented. They use local representations, hashing, atld multiple scales of resolution to approximate functions which are piece-wise continuous. Inspired by Albus's CMAC model, the algorithms learn orders of magnitude more rapidly than typical implementations of back propagation, while often achieving comparable qualities of generalization. Furthermore, unlike most traditional function approximation methods, the algorithms are well suited for… CONTINUE READING
70 Extracted Citations
10 Extracted References
Similar Papers

Citing Papers

Publications influenced by this paper.
Showing 1-10 of 70 extracted citations

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 10 references

Brain, Behavior and Rohotic6

  • J. S. Albus
  • Byte Books,
  • 1981
Highly Influential
6 Excerpts

Learning with localized receptive fields

  • Omohundro
  • Touretzky , Hinton , and Sejnowski , editors…
  • 1988

Application of a general learning algorithm to the control of robotic manipulators

  • Thomas Miller
  • International Journal of Robotic 6 Re 6 earch
  • 1987

Clauification and Regreuion Tree6

  • L. Breiman, J. H. Friedman, R. A. Olshen, C. J. Stone
  • 1984
1 Excerpt

Similar Papers

Loading similar papers…