Full-Text Search:
Home|About CNKI|User Service|中文
Add to Favorite Get Latest Update

Nonlinear Recognition Based on the Genetic Algorithms

WANG Jing-fang(Department of Information and Electron Engineering,Hunan International Economics University,Changsha 410205,China)  
This paper designs a model structure of the artificial neural network, optimizes the model parameters based on genetic algorithms and applies it to nonlinear pattern recognition.The use of the genetic algorithm proves to be effective in both linear and nonlinear problems and it is easier,more convenient and better than the design of piecewise linear classifiers and the error back-propagation algorithm.The example shows that the desirable result can be achieved by propagating 40 eras and the recognition rate is up to 100% by means of the genetic algorithm.
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©CNKI All Rights Reserved