On the Identification and Generation of Discrete-Time Chaotic Systems with Recurrent Neural Networks

We address the identification and generation of the discrete-time chaotic system (DTCS) with a two-layered recurrent neural network (RNN). First, we propose an identification procedure of the DTCS in which the RNN is required to have less layers than in the conventional procedures. Next, based on Li–Yorke theorem, we propose a generation procedure which enables us to predict a range of chaotic behavior of the DTCS in advance. Simulation results demonstrate that the proposed identification procedure, employing the Levenberg–Marquardt algorithm and a two-layered RNN, requires lower computational complexity than the conventional identification procedures at comparable performance.

[1]  Chia-Nan Ko,et al.  Identification of Chaotic System Using Fuzzy Neural Networks with Time-Varying Learning Algorithm , 2012 .

[2]  Yuxia Li,et al.  The Generation, Analysis, and Circuit Implementation of a New Memristor Based Chaotic System , 2013 .

[3]  O. Kisi,et al.  Time series analysis on marine wind-wave characteristics using chaos theory , 2015 .

[4]  M. Marchesi,et al.  Learning of Chua's circuit attractors by locally recurrent neural networks , 2001 .

[5]  J. Yorke,et al.  Period Three Implies Chaos , 1975 .

[6]  E. Cook,et al.  Methods of Dendrochronology - Applications in the Environmental Sciences , 1991 .

[7]  Ingo Fischer,et al.  Fast Random Bit Generation Using a Chaotic Laser: Approaching the Information Theoretic Limit , 2013, IEEE Journal of Quantum Electronics.

[8]  Chin-Teng Lin,et al.  Identification and Prediction of Dynamic Systems Using an Interactively Recurrent Self-Evolving Fuzzy Neural Network , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Shigeru Tachibana,et al.  Detection and control of combustion instability based on the concept of dynamical system theory. , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

[10]  Martin Casdagli,et al.  Nonlinear prediction of chaotic time series , 1989 .

[11]  Iickho Song,et al.  Identification of Finite State Automata With a Class of Recurrent Neural Networks , 2010, IEEE Transactions on Neural Networks.

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

[13]  Hilaire Bertrand Fotsin,et al.  Dynamics, Analysis and Implementation of a Multiscroll Memristor-Based Chaotic Circuit , 2016, Int. J. Bifurc. Chaos.

[14]  Shijian Lu,et al.  Accurate recognition of words in scenes without character segmentation using recurrent neural network , 2017, Pattern Recognit..

[15]  Ching-Hung Lee,et al.  Identification and control of dynamic systems using recurrent fuzzy neural networks , 2000, IEEE Trans. Fuzzy Syst..

[16]  Alexey A. Koronovskii,et al.  Generalized synchronization of chaos for secure communication: Remarkable stability to noise , 2010, 1302.4067.

[17]  Shing-Tai Pan,et al.  Identification of Chaotic Systems by Neural Network with Hybrid Learning Algorithm , 2008, IMECS.

[18]  R. Ghanem,et al.  A wavelet-based approach for model and parameter identification of non-linear systems , 2001 .

[19]  Miguel Pinzolas,et al.  Neighborhood based Levenberg-Marquardt algorithm for neural network training , 2002, IEEE Trans. Neural Networks.

[20]  Ming Zhou,et al.  Adaptive Multi-Compositionality for Recursive Neural Network Models , 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[21]  Zhang Yi,et al.  Multistability of discrete-time recurrent neural networks with unsaturating piecewise linear activation functions , 2004, IEEE Transactions on Neural Networks.

[22]  Aude Billard,et al.  A dynamical system approach to realtime obstacle avoidance , 2012, Autonomous Robots.

[23]  Hossein Mirzaee,et al.  Long-term prediction of chaotic time series with multi-step prediction horizons by a neural network with Levenberg–Marquardt learning algorithm , 2009 .

[24]  Yevgeniy V. Bodyanskiy,et al.  Hybrid adaptive wavelet-neuro-fuzzy system for chaotic time series identification , 2013, Inf. Sci..