Automatic implementation of totalistic cellular automata through polynomial cellular neural networks

The learning procedures of cellular automata and cellular neural networks are not trivial tasks. They have been addressed previously with several techniques such as genetic algorithms, although they are computationally costly. As a contribution in the area of polynomial cellular neural networks, in this paper we present a novel method to determine automatically the optimum order of the polynomial term, and the generalized system of equations for a polynomial cellular neural network that implements any totalistic cellular automata behavior. Such advances can be coupled with a quadratic programming algorithm in order to radically boost training performance and dispense human intervention.

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

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

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

[4]  Bharathwaj Muthuswamy,et al.  Optimal CNN Templates for Linearly-Separable One-Dimensional Cellular Automata , 2007, Int. J. Bifurc. Chaos.

[5]  Giovanni Egidio Pazienza,et al.  Computing the Weights of Polynomial Cellular Neural Networks Using Quadratic Programming , 2009, CIARP.

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

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

[8]  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.

[9]  Leon O. Chua,et al.  Cellular neural networks: applications , 1988 .

[10]  Bastien Chopard,et al.  Cellular Automata Modeling of Physical Systems , 1999, Encyclopedia of Complexity and Systems Science.

[11]  Joos Vandewalle,et al.  Data security issues, cryptographic protection methods, and the use of cellular neural networks and cellular automata , 1998, 1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359).

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

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

[14]  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.

[15]  M. Brucoli,et al.  Discrete-time cellular neural networks for associative memories with learning and forgetting capabilities , 1995 .

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

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

[18]  O. Castillo,et al.  2013 IEEE Workshop on Hybrid Intelligent Models and Applications, HIMA 2013, Singapore, April 16-19, 2013 , 2013, HIMA.

[19]  Sergey Pudov.  Learning of cellular neural networks , 2001, Future Gener. Comput. Syst..

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

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

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

[23]  Zhigang Zeng,et al.  Associative memories based on continuous-time cellular neural networks designed using space-invariant cloning templates , 2009, Neural Networks.

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

[25]  Sergio Taraglio,et al.  A practical use of cellular neural networks: the stereo-vision problem as an optimisation , 2000, Machine Vision and Applications.

[26]  Leon O. Chua,et al.  The CNN Universal Machine is as universal as a Turing Machine , 1996 .