The improvement of a fuzzy neural network based on backpropagation
Qiang Hua, Ming-Hu Ha · 2003
Some discussions on the fuzzy neural network architecture and algorithm have been put forward, whose weights are given as special fuzzy numbers, such as triangular fuzzy numbers. In this paper, we introduce the conception of strong L-R type fuzzy number, and derive a learning algorithm based on BP algorithm via level sets of strong L-R type fuzzy numbers. The special fuzzy number is weakened to the common case. Then the range of application is enlarged. Finally, the initial experiment in fuzzy classification is shown.