A root location training method for polynomial cellular neural networks that implements totalistic cellular automata

The Polynomial Cellular Neural Network (PCNN) is a powerful non-linear processor that is capable of classifying non-linearly separable data points with a single neuron. Despite the capabilities of this model, the determination of the synaptic weights is not a trivial task. In this paper we present the root location training method as an effective, straightforward and high-speed procedure. Such method obtains the synaptic weights of a PCNN that implements any totalistic cellular automata behavior, dispensing the usage of heuristic methods such as genetic algorithms or numerical approaches such as quadratic programming procedures.

[1]  Ronald Tetzlaff,et al.  Modeling nonlinear systems with cellular neural networks , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[2]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[3]  Josef A. Nossek.  Design and Learning with Cellular Neural Networks , 1996, Int. J. Circuit Theory Appl..

[4]  Leon O. Chua,et al.  Genetic algorithm for CNN template learning , 1993 .

[5]  Andrew Ilachinski,et al.  Cellular Automata: A Discrete Universe , 2001 .

[6]  Igor N. Aizenberg,et al.  Processing of noisy and small-detailed gray-scale images using cellular neural networks , 1997, J. Electronic Imaging.

[7]  Janez Puhan,et al.  A rigorous design method for binary cellular neural networks , 1998, Int. J. Circuit Theory Appl..

[8]  Leon O. Chua,et al.  The CNN paradigm , 1993 .

[9]  Michele Zamparelli,et al.  Genetically Trained Cellular Neural Networks , 1997, Neural Networks.

[10]  Giovanni Egidio Pazienza,et al.  Complexity Index of Outer-Totalistic Binary Cellular Automata with Arbitrary Dimension and Neighborhood , 2012, Int. J. Bifurc. Chaos.

[11]  Leon O. Chua,et al.  The CNN is universal as the Turing machine , 1993 .

[12]  Leon O. Chua,et al.  UNIVERSAL CNN CELLS , 1999 .

[13]  George S. Moschytz,et al.  Learning algorithms for cellular neural networks , 1998, ISCAS '98. Proceedings of the 1998 IEEE International Symposium on Circuits and Systems (Cat. No.98CH36187).

[14]  Akio Ushida,et al.  Adaptive Simulated Annealing in CNN Template Learning , 1999 .

[15]  Giovanni Egidio Pazienza,et al.  Automatic implementation of totalistic cellular automata through polynomial cellular neural networks , 2013, 2013 IEEE Workshop on Hybrid Intelligent Models and Applications (HIMA).

[16]  R. Tetzlaff,et al.  Evolutionary learning strategies for cellular neural networks , 2000, Proceedings of the 2000 6th IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA 2000) (Cat. No.00TH8509).

[17]  Tamás Szirányi,et al.  Texture classification by cellular neural network and genetic learning , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 2 - Conference B: Computer Vision & Image Processing. (Cat. No.94CH3440-5).

[18]  Bastien Chopard,et al.  Cellular Automata Modeling of Physical Systems: Index , 1998 .

[19]  R. Tetzlaff,et al.  A learning algorithm for cellular neural networks (CNN) solving nonlinear partial differential equations , 1995, Proceedings of ISSE'95 - International Symposium on Signals, Systems and Electronics.

[20]  Giuseppe Grassi,et al.  Learning algorithm for pattern classification using cellular neural networks , 2000 .

[21]  Giovanni Egidio Pazienza,et al.  Polynomial Cellular Neural Networks for Implementing Semitotalistic Cellular Automata , 2007 .

[22]  Ákos Zarándy.  The art of CNN template design , 1999, Int. J. Circuit Theory Appl..

[23]  Giovanni Egidio Pazienza,et al.  New properties of 2D Cellular Automata found through Polynomial Cellular Neural Networks , 2009, 2009 International Joint Conference on Neural Networks.

[24]  Giovanni Egidio Pazienza,et al.  Learning in Polynomial Cellular neural networks using quadratic programming , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[25]  Ákos Zarándy.  The art of CNN template design , 1999 .

[26]  Giovanni Egidio Pazienza,et al.  The Game of Life Using Polynomial Discrete Time Cellular Neural Networks , 2007, Analysis and Design of Intelligent Systems using Soft Computing Techniques.

[27]  Leon O. Chua,et al.  A Nonlinear Dynamics Perspective of Wolfram's New Kind of Science Part I: Threshold of Complexity , 2002, Int. J. Bifurc. Chaos.