Universal approximation with uninorm-based fuzzy neural networks

Fuzzy neural networks are hybrid models capable to approximate functions with high precision and to generate transparent models, enabling the extraction of valuable information from the resulting topology. In this paper we will show that the recently proposed fuzzy neural network based on weighted uninorms aggregations uniformly approximates any real functions on any compact set. We will describe the network topology and inference mechanism and show that the universal approximation property of this network is valid for a given choice of operators.

[1]  Witold Pedrycz,et al.  Fuzzy Systems Engineering - Toward Human-Centric Computing , 2007 .

[2]  Vladik Kreinovich,et al.  Universal approximation theorem for uninorm-based fuzzy systems modeling , 2003, Fuzzy Sets Syst..

[3]  Lotfi A. Zadeh,et al.  Fuzzy sets and systems , 1990 .

[4]  Fernando Gomide,et al.  Learning in recurrent, hybrid neurofuzzy networks , 2002, 2002 IEEE World Congress on Computational Intelligence. 2002 IEEE International Conference on Fuzzy Systems. FUZZ-IEEE'02. Proceedings (Cat. No.02CH37291).

[5]  Fernando Gomide,et al.  Uninetworks in time series forecasting , 2009, NAFIPS 2009 - 2009 Annual Meeting of the North American Fuzzy Information Processing Society.

[6]  Ronald R. Yager,et al.  Uninorm aggregation operators , 1996, Fuzzy Sets Syst..

[7]  Witold Pedrycz,et al.  Logic Minimization as an Efficient Means of Fuzzy Structure Discovery , 2008, IEEE Transactions on Fuzzy Systems.

[8]  F. Gomide,et al.  Participatory Learning in Power Transformers Thermal Modeling , 2008, IEEE Transactions on Power Delivery.

[9]  Witold Pedrycz,et al.  Fuzzy Set Based Neural Networks: Structure, Learning and Application , 1999, J. Adv. Comput. Intell. Intell. Informatics.

[10]  Ronald R. Yager,et al.  Uninorms in fuzzy systems modeling , 2001, Fuzzy Sets Syst..

[11]  Witold Pedrycz,et al.  Heterogeneous fuzzy logic networks: fundamentals and development studies , 2004, IEEE Transactions on Neural Networks.

[12]  Witold Pedrycz,et al.  Logic-Based Fuzzy Neurocomputing With Unineurons , 2006, IEEE Transactions on Fuzzy Systems.

[13]  Witold Pedrycz,et al.  Logic-oriented neural networks for fuzzy neurocomputing , 2009, Neurocomputing.

[14]  Fernando Gomide,et al.  New uninorm-based neuron model and fuzzy neural networks , 2010, 2010 Annual Meeting of the North American Fuzzy Information Processing Society.

[15]  Witold Pedrycz,et al.  Fuzzy neural networks and neurocomputations , 1993 .

[16]  Witold Pedrycz,et al.  Uninorm-Based Logic Neurons as Adaptive and Interpretable Processing Constructs , 2007, Soft Comput..

[17]  F. Gomide,et al.  Nullneurons-Based Hybrid Neurofuzzy Network , 2007, NAFIPS 2007 - 2007 Annual Meeting of the North American Fuzzy Information Processing Society.

[18]  Bernard De Baets,et al.  The functional equations of Frank and Alsina for uninorms and nullnorms , 2001, Fuzzy Sets Syst..

[19]  Witold Pedrycz,et al.  Logic-based fuzzy networks: A study in system modeling with triangular norms and uninorms , 2009, Fuzzy Sets Syst..