Fuzzy Neural Network Using Rectangle Functions
Xing Jinsheng,Wan Baiwu
(Xi'an Jiaotong University, Xi'an 710049,  China)

Abstract:  Fuzzy neural network(FNN) using rectangle functions is constructed by partitioning input space into many disjoint hyper-cubes with the same size. FNN is constant in each of the hyper-cubes.If andonly if an input sample drops into a hyper-cube would the corresponding samplebe memorized through coding. Moreover,FNN can generate fuzzy rules automatically.For the control of a nonlinear system,a theorem about static error shows that static error can be decreased for small enough partition of the input space.Simulation example shows that the result is satisfactory.
Keywords: fuzzy neural network;nonlinear system;rectangle functions