Polynomial Discrete Time Cellular Neural Networks to solve the XOR problem

Some papers discuss different options to improve the capabilities of cellular neural networks (CNN). The principal point is that a single layer CNN can not solve problems with linearly nonseparable data. In this paper a new model called polynomial discrete time cellular neural networks is presented. This model has a very simple nonlinear term that can improve the performance of the network. The results show how it is possible to solve the XOR problem. The templates of the entire network are computed using genetic algorithm

[1]  Osman N. Uçan,et al.  Cellular neural network with trapezoidal activation function , 2005, Int. J. Circuit Theory Appl..

[2]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[3]  Akio Ushida,et al.  Templates and algorithms for two-layer cellular neural networks , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[4]  Hubert Harrer.  Discrete time cellular neural networks , 1992, Int. J. Circuit Theory Appl..

[5]  Alexander S. Poznyak,et al.  Polynomial artificial neural network and genetic algorithm for the identification and control of non , 2002 .

[6]  A. G. Ivakhnenko,et al.  Polynomial Theory of Complex Systems , 1971, IEEE Trans. Syst. Man Cybern..

[7]  Nils J. Nilsson,et al.  The Mathematical Foundations of Learning Machines , 1990 .

[8]  Y. Shin.  Modified Bernstein polynomials and their connectionist interpretation , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[9]  Marvin Minsky,et al.  Perceptrons: An Introduction to Computational Geometry , 1969 .

[10]  Sheng Chen,et al.  Recursive prediction error parameter estimator for non-linear models , 1989 .

[11]  Vincenzo Piuri,et al.  Experimental neural networks for prediction and identification , 1996 .

[12]  Eduardo Gómez Ramírez.  Cellular Neural Networks Learning using Genetic Algorithm , 2002 .

[13]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[14]  M. Balsi.  Generalized CNN: Potentials of a CNN with non-uniform weights , 1992, CNNA '92 Proceedings Second International Workshop on Cellular Neural Networks and Their Applications.

[15]  Robert J. Marks,et al.  Electric load forecasting using an artificial neural network , 1991 .

[16]  Sheng Chen,et al.  Representations of non-linear systems: the NARMAX model , 1989 .

[17]  John Y. Cheung,et al.  Polynomial and standard higher order neural network , 1993, IEEE International Conference on Neural Networks.

[18]  Eduardo Gómez-Ramírez,et al.  Forecasting Time Series with a New Architecture for Polynomial Artificial Neural Network , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[19]  Joydeep Ghosh,et al.  Approximation of multivariate functions using ridge polynomial networks , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[20]  Kaddour Najim,et al.  Forecasting time series with a new architecture for polynomial artificial neural network , 2007, Appl. Soft Comput..

[21]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[22]  Mark A. Franklin,et al.  A Learning Identification Algorithm and Its Application to an Environmental System , 1975, IEEE Transactions on Systems, Man, and Cybernetics.