A new set of sufficient conditions based on coupling parameters for synchronization of Hopfield like Chaotic Neural Networks

In this paper, we consider a Hopfield like Chaotic Neural Networks which have both self-coupling and non-invertible activation functions. We show that the interactions between neurons can be used as a means of chaos generation or suppression to neuron’s outputs when more adaptability or stability is required. Furthermore, a new set of sufficient conditions based on coupling weights is proposed so that the synchronization of all neuron’s outputs with each other is guaranteed, when all neuron’s have identical activation functions. Finally, the effectiveness of the proposed approach is evaluated by performing simulations on three illustrative examples.

[1]  Arash Mohammadi,et al.  Design of a chaotic neural network by using chaotic nodes and NDRAM network , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[2]  A Babloyantz,et al.  Computation with chaos: a paradigm for cortical activity. , 1994, Proceedings of the National Academy of Sciences of the United States of America.

[3]  Elif Derya Übeyli,et al.  Recurrent neural networks employing Lyapunov exponents for EEG signals classification , 2005, Expert Syst. Appl..

[4]  Louis M. Pecora,et al.  Synchronizing chaotic circuits , 1991 .

[5]  Raymond S. T. Lee.  A transient-chaotic autoassociative network (TCAN) based on Lee oscillators , 2004, IEEE Transactions on Neural Networks.

[6]  Terrence J. Sejnowski,et al.  The Computational Brain , 1996, Artif. Intell..

[7]  Guanrong Chen,et al.  Global synchronization and asymptotic stability of complex dynamical networks , 2006, IEEE Transactions on Circuits and Systems II: Express Briefs.

[8]  L. Wang,et al.  Interactions of neural networks: models for distraction and concentration. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[9]  Carroll,et al.  Synchronization in chaotic systems. , 1990, Physical review letters.

[10]  Toshimichi Saito,et al.  Grouping synchronization in a pulse-coupled network of chaotic spiking oscillators , 2004, IEEE Transactions on Neural Networks.

[11]  Heidar Ali Talebi,et al.  A Novel Robust Impulsive Chaos Synchronization Approach for Uncertain Complex Dynamical Networks , 2009, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[12]  Toshimichi Saito,et al.  Basic dynamics from a pulse-coupled network of autonomous integrate-and-fire chaotic circuits , 2002, IEEE Trans. Neural Networks.

[13]  Duncan J. Watts,et al.  Collective dynamics of ‘small-world’ networks , 1998, Nature.

[14]  Jacek M. Zurada,et al.  Cellular Neural Networks With Transient Chaos , 2007, IEEE Transactions on Circuits and Systems II: Express Briefs.

[15]  Guanrong Chen,et al.  Chaos synchronization of general complex dynamical networks , 2004 .

[16]  C. M. Lim,et al.  Characterization of EEG - A comparative study , 2005, Comput. Methods Programs Biomed..

[17]  Robert C. Hilborn,et al.  Chaos and Nonlinear Dynamics , 2000 .

[18]  L. Wang,et al.  Oscillations and chaos in neural networks: an exactly solvable model. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[19]  K. Aihara,et al.  Chaotic neural networks , 1990 .

[20]  Moayed Daneshyari,et al.  A neurochaotic PSO-guided network based upon perturbed duffing oscillator , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[21]  Lipo Wang,et al.  Interactions between neural networks: a mechanism for tuning chaos and oscillations , 2007, Cognitive Neurodynamics.

[22]  Johan A. K. Suykens,et al.  Master-Slave Synchronization of Lur'e Systems with Time-Delay , 2001, Int. J. Bifurc. Chaos.

[23]  James Nga-Kwok Liu,et al.  Using LIDAR doppler velocity data and chaotic oscillatory-based neural network for the forecast of meso-scale wind field , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).