论文信息 - A novel fuzzy neural network and its approximation capability

A novel fuzzy neural network and its approximation capability

The polygonal fuzzy numbers are employed to define a new fuzzy arithmetic. A novel extension principle is also introduced for the increasing function σ: ℝ → ℝ. Thus it is convenient to construct a fuzzy neural network model with succinct learning algorithms. Such a system possesses some universal approximation capabilities, that is, the corresponding three layer feedforward fuzzy neural networks can be universal approximators to the continuously increasing fuzzy functions.

Puyin Liu | P. Liu | Puyin Liu

[1] Ah Chung Tsoi,et al. Universal Approximation Using Feedforward Neural Networks: A Survey of Some Existing Methods, and Some New Results , 1998, Neural Networks.

[2] Hao Wang,et al. Approximation capability of regular fuzzy neural networks to continuous fuzzy functions , 1999 .

[3] Hung T. Nguyen,et al. A note on the extension principle for fuzzy sets , 1978 .

[4] H. Ishibuchi,et al. A learning algorithm of fuzzy neural networks with triangular fuzzy weights , 1995 .

[5] Puyin Liu,et al. Analyses of regular fuzzy neural networks for approximation capabilities , 2000, Fuzzy Sets Syst..

[6] Hong Chen,et al. Approximation capability in C(R¯n) by multilayer feedforward networks and related problems , 1995, IEEE Trans. Neural Networks.

[7] James J. Buckley,et al. Can neural nets be universal approximators for fuzzy functions? , 1999, Fuzzy Sets Syst..

[8] James J. Buckley,et al. Can fuzzy neural nets approximate continuous fuzzy functions , 1994 .

[9] Maxwell B. Stinchcombe,et al. Neural network approximation of continuous functionals and continuous functions on compactifications , 1999, Neural Networks.