Design and analysis of a novel chaotic diagonal recurrent neural network

Abstract A chaotic neural network model with logistic mapping is proposed to improve the performance of the conventional diagonal recurrent neural network. The network shows rich dynamic behaviors that contribute to escaping from a local minimum to reach the global minimum easily. Then, a simple parameter modulated chaos controller is adopted to enhance convergence speed of the network. Furthermore, an adaptive learning algorithm with the robust adaptive dead zone vector is designed to improve the generalization performance of the network, and weights convergence for the network with the adaptive dead zone vectors is proved in the sense of Lyapunov functions. Finally, the numerical simulation is carried out to demonstrate the correctness of the theory.

[1]  Tao Wang,et al.  A novel GCM chaotic neural network for information processing , 2012 .

[2]  Feng Liu,et al.  A new chaotic Hopfield neural network and its synthesis via parameter switchings , 2013, Neurocomputing.

[3]  Amir F. Atiya,et al.  New results on recurrent network training: unifying the algorithms and accelerating convergence , 2000, IEEE Trans. Neural Networks Learn. Syst..

[4]  Shogo Miyake,et al.  Effects of correlation among stored patterns on associative dynamics of chaotic neural network , 2005 .

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

[6]  Kazuyuki Aihara,et al.  Global searching ability of chaotic neural networks , 1999 .

[7]  Kazuyuki Aihara,et al.  Associative Dynamics in a Chaotic Neural Network , 1997, Neural Networks.

[8]  Ho Sun Chung,et al.  Chaotic recurrent neural networks and their application to speech recognition , 1996, Neurocomputing.

[9]  Qing Song,et al.  On the Weight Convergence of Elman Networks , 2010, IEEE Transactions on Neural Networks.

[10]  Jiahai Wang,et al.  A method to improve the transiently chaotic neural network , 2004, Neurocomputing.

[11]  Kazuyuki Aihara,et al.  Partial state feedback control of chaotic neural network and its application , 2007 .

[12]  Masaya Ohta,et al.  Chaotic neural networks with reinforced self-feedbacks and its application to N-Queen problem , 2002, Math. Comput. Simul..

[13]  Jinde Cao,et al.  Cryptography based on delayed chaotic neural networks , 2006 .

[14]  Xiang Li,et al.  Chaotifying linear Elman networks , 2002, IEEE Trans. Neural Networks.

[15]  Kejun Wang,et al.  Optimization of learning algorithms for Chaotic Diagonal Recurrent Neural Networks , 2010, 2010 International Conference on Intelligent Control and Information Processing.

[16]  Abdulrahman H. Bajodah,et al.  Real time adaptive nonlinear model inversion control of a twin rotor MIMO system using neural networks , 2012, Eng. Appl. Artif. Intell..

[17]  Derong Liu,et al.  On the global output convergence of a class of recurrent neural networks with time-varying inputs , 2005, Neural Networks.

[18]  Carsten Peterson,et al.  A New Method for Mapping Optimization Problems Onto Neural Networks , 1989, Int. J. Neural Syst..

[19]  Kwang Y. Lee,et al.  Diagonal recurrent neural networks for dynamic systems control , 1995, IEEE Trans. Neural Networks.

[20]  W. Freeman.  Simulation of chaotic EEG patterns with a dynamic model of the olfactory system , 1987, Biological Cybernetics.

[21]  Xianglong Tang,et al.  A new parameter control method for S-GCM , 2005, Pattern Recognit. Lett..

[22]  Paris A. Mastorocostas.  A Block-Diagonal Recurrent Fuzzy Neural Network for Dynamic System Identification , 2007, 2007 IEEE International Fuzzy Systems Conference.

[23]  Seyyed Ali Seyyedsalehi,et al.  Design of a chaotic neural network for training and retrieval of grayscale and binary patterns , 2011, Neurocomputing.

[24]  Reza Mazrooei-Sebdani,et al.  Bifurcations and chaos in a discrete-time-delayed Hopfield neural network with ring structures and different internal decays , 2013, Neurocomputing.

[25]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[26]  Qingshan Liu,et al.  Finite-Time Convergent Recurrent Neural Network With a Hard-Limiting Activation Function for Constrained Optimization With Piecewise-Linear Objective Functions , 2011, IEEE Transactions on Neural Networks.

[27]  Kazuyuki Aihara,et al.  Chaotic simulated annealing by a neural network model with transient chaos , 1995, Neural Networks.