A FUZZY CONTROLLING METHOD FOR NEURAL NETWORK TRAINING
DOI:
CSTR:
Author:
Affiliation:

Clc Number:

TP18

Fund Project:

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    A fuzzy controlling method was proposed. It controls the training parameters according to the property of training samples, i.e.adjusts the study rate with fuzzy rules. The fuzzy rules are determined by the distribution of the training set and the important level of each kind of samples. The classification rate can be improved in this way and the fast convergence property can be achieved.

    Reference
    Related
    Cited by
Get Citation

Wang Yunhong Liu Guosui Wang Yiding Gu Hong. A FUZZY CONTROLLING METHOD FOR NEURAL NETWORK TRAINING[J]. Journal of Infrared and Millimeter Waves,1997,16(4):307~310

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:
  • Revised:
  • Adopted:
  • Online:
  • Published:
Article QR Code