Chaos on compact manifolds: Differentiable synchronizations beyond the Takens theorem.

This paper shows that a large class of fading memory state-space systems driven by discrete-time observations of dynamical systems defined on compact manifolds always yields continuously differentiable synchronizations. This general result provides a powerful tool for the representation, reconstruction, and forecasting of chaotic attractors. It also improves previous statements in the literature for differentiable generalized synchronizations, whose existence was so far guaranteed for a restricted family of systems and was detected using Hölder exponent-based criteria.

[1]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[2]  Pyragas,et al.  Weak and strong synchronization of chaos. , 1996, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[3]  Herbert Jaeger,et al.  Echo State Property Linked to an Input: Exploring a Fundamental Characteristic of Recurrent Neural Networks , 2013, Neural Computation.

[4]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

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

[6]  Louis M. Pecora,et al.  Fundamentals of synchronization in chaotic systems, concepts, and applications. , 1997, Chaos.

[7]  E. Lorenz Deterministic nonperiodic flow , 1963 .

[8]  Thomas L. Carroll,et al.  Using reservoir computers to distinguish chaotic signals , 2018, Physical Review E.

[9]  Juan-Pablo Ortega,et al.  Reservoir Computing Universality With Stochastic Inputs , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[10]  J. Huke Embedding Nonlinear Dynamical Systems: A Guide to Takens' Theorem , 2006 .

[11]  G Manjunath,et al.  Stability and memory-loss go hand-in-hand: three results in dynamics and computation , 2020, Proceedings of the Royal Society A.

[12]  T. Pereira,et al.  Synchronisation of chaos and its applications , 2017 .

[13]  Jaideep Pathak,et al.  Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data. , 2017, Chaos.

[14]  Neil Genzlinger A. and Q , 2006 .

[15]  Joel H. Shapiro,et al.  A Fixed-Point Farrago , 2016 .

[16]  F. Takens Detecting strange attractors in turbulence , 1981 .

[17]  Toshiyuki Yamane,et al.  Recent Advances in Physical Reservoir Computing: A Review , 2018, Neural Networks.

[18]  P. Alam ‘A’ , 2021, Composites Engineering: An A–Z Guide.

[19]  Allen G Hart,et al.  Embedding and approximation theorems for echo state networks , 2019, Neural Networks.

[20]  H. Berendse,et al.  Generalized Synchronization of MEG Recordings in Alzheimer’s Disease: Evidence for Involvement of the Gamma Band , 2002, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[21]  Jaideep Pathak,et al.  Model-Free Prediction of Large Spatiotemporally Chaotic Systems from Data: A Reservoir Computing Approach. , 2018, Physical review letters.

[22]  Allen G. Hart,et al.  Echo State Networks trained by Tikhonov least squares are L2(μ) approximators of ergodic dynamical systems , 2020, Physica D: Nonlinear Phenomena.

[23]  Lukas Gonon,et al.  Risk bounds for reservoir computing , 2019, ArXiv.

[24]  Giulio Ruffini,et al.  Detection of Generalized Synchronization using Echo State Networks , 2017, Chaos.

[25]  K. Aberer,et al.  German National Research Center for Information Technology , 2007 .

[26]  Lorenzo Livi,et al.  Learn to Synchronize, Synchronize to Learn , 2021, Chaos.

[27]  Miss A.O. Penney (b) , 1974, The New Yale Book of Quotations.

[28]  Danielle S Bassett,et al.  Invertible generalized synchronization: A putative mechanism for implicit learning in neural systems. , 2020, Chaos.

[29]  Lorenzo Livi,et al.  Interpreting Recurrent Neural Networks Behaviour via Excitable Network Attractors , 2018, Cognitive Computation.

[30]  E. Ott Chaos in Dynamical Systems: Contents , 2002 .

[31]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[32]  Lorenzo Rosasco,et al.  Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review , 2016, International Journal of Automation and Computing.

[33]  Louis M Pecora,et al.  Synchronization of chaotic systems. , 2015, Chaos.

[34]  Parlitz,et al.  General approach for chaotic synchronization with applications to communication. , 1995, Physical Review Letters.

[35]  Michael Small,et al.  The reservoir's perspective on generalized synchronization. , 2019, Chaos.

[36]  J. Yorke,et al.  Differentiable generalized synchronization of chaos , 1997 .

[37]  Juan-Pablo Ortega,et al.  Echo state networks are universal , 2018, Neural Networks.

[38]  Gonzalo Alvarez,et al.  Breaking projective chaos synchronization secure communication using filtering and generalized synchronization , 2004, Chaos, Solitons & Fractals.

[39]  Juan-Pablo Ortega,et al.  Universal discrete-time reservoir computers with stochastic inputs and linear readouts using non-homogeneous state-affine systems , 2017, J. Mach. Learn. Res..

[40]  C. Stam,et al.  Disturbed functional connectivity in brain tumour patients: Evaluation by graph analysis of synchronization matrices , 2006, Clinical Neurophysiology.

[41]  Parlitz,et al.  Generalized synchronization, predictability, and equivalence of unidirectionally coupled dynamical systems. , 1996, Physical review letters.

[42]  Juan-Pablo Ortega,et al.  Differentiable reservoir computing , 2019, J. Mach. Learn. Res..

[43]  H. N. Mhaskar,et al.  Neural Networks for Optimal Approximation of Smooth and Analytic Functions , 1996, Neural Computation.

[44]  Mw Hirsch,et al.  Chaos In Dynamical Systems , 2016 .

[45]  陈关荣,et al.  A Chaotic Communication Scheme Based on Generalized Synchronization and Hash Functions , 2004 .

[46]  Edward Ott,et al.  Attractor reconstruction by machine learning. , 2018, Chaos.

[47]  Michael B. Matthews,et al.  On the uniform approximation of nonlinear discrete-time fading-memory systems using neural network models , 1992 .

[48]  S. Ana,et al.  Topology , 2018, International Journal of Mathematics Trends and Technology.

[49]  L. Tsimring,et al.  Generalized synchronization of chaos in directionally coupled chaotic systems. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.