Recurrent algebraic fuzzy neural networks based on fuzzy numbers

A hybrid structure, recurrent algebraic fuzzy neural networks (RAFNN) using fully connected recurrent neural network architecture is proposed. The hybrid structure is based on neural network topology and fuzzy algebraic systems. All the operations are defined in the frame of fuzzy arithmetic using triangular fizzy numbers (usually non-symmetric). The experimental results demonstrate the capability of algorithm and the possibility to use successfully fuzzy numbers in recurrent architecture in order to acquire a dynamic behavior.

[1]  Didier Dubois,et al.  Fuzzy sets and systems ' . Theory and applications , 2007 .

[2]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[3]  R. Bone,et al.  Two constructive algorithms for improved time series processing with recurrent neural networks , 2000, Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501).

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

[5]  Ronald J. Williams,et al.  Experimental Analysis of the Real-time Recurrent Learning Algorithm , 1989 .

[6]  Abraham Kandel,et al.  Analytic fuzzy RBF neural network , 1998, 1998 Conference of the North American Fuzzy Information Processing Society - NAFIPS (Cat. No.98TH8353).