Learning strange attractors with reservoir systems

DOI10.1088/1361-6544/ACE492zbMATH Open1525.37020arXiv2108.05024OpenAlexW3187680631MaRDI QIDQ6169729FDOQ6169729

Authors: Lyudmila Grigoryeva, Allen Hart, Juan-Pablo Ortega 

Publication date: 15 August 2023

Published in: Nonlinearity (Search for Journal in Brave)

Abstract: This paper shows that the celebrated Embedding Theorem of Takens is a particular case of a much more general statement according to which, randomly generated linear state-space representations of generic observations of an invertible dynamical system carry in their wake an embedding of the phase space dynamics into the chosen Euclidean state space. This embedding coincides with a natural generalized synchronization that arises in this setup and that yields a topological conjugacy between the state-space dynamics driven by the generic observations of the dynamical system and the dynamical system itself. This result provides additional tools for the representation, learning, and analysis of chaotic attractors and sheds additional light on the reservoir computing phenomenon that appears in the context of recurrent neural networks.

Full work available at URL: https://arxiv.org/abs/2108.05024

Recommendations

• Learning dynamics by reservoir computing (In Memory of Prof. Pavol Brunovský)
• Generalised synchronisations, embeddings, and approximations for continuous time reservoir computers
• Learning Theory for Dynamical Systems
• Embedding and approximation theorems for echo state networks
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data

zbMATH Keywords

dynamical systemsattractorgeneralized synchronizationreservoir computingecho state propertyTakens embeddingfading memory property

Mathematics Subject Classification ID

Strange attractors, chaotic dynamics of systems with hyperbolic behavior (37D45) Dynamical systems involving smooth mappings and diffeomorphisms (37C05) Attractors and repellers of smooth dynamical systems and their topological structure (37C70)

Cites Work

• Title not available (Why is that?)
• Deterministic Nonperiodic Flow
• Manifolds, tensor analysis, and applications.
• Embedology
• The synchronization of chaotic systems
• Title not available (Why is that?)
• Differential Topology
• Title not available (Why is that?)
• Title not available (Why is that?)
• Chaos in Dynamical Systems
• Title not available (Why is that?)
• Fundamentals of synchronization in chaotic systems, concepts, and applications
• Title not available (Why is that?)
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• Reservoir computing approaches to recurrent neural network training
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data
• Approximating nonlinear fading-memory operators using neural network models
• Memory and forecasting capacities of nonlinear recurrent networks
• Embedding and approximation theorems for echo state networks
• Echo state networks are universal
• Dimension reduction in recurrent networks by canonicalization
• Echo state networks trained by Tikhonov least squares are \(L^2(\mu)\) approximators of ergodic dynamical systems
• Fading memory echo state networks are universal
• Echo state property linked to an input: exploring a fundamental characteristic of recurrent neural networks
• Invertible generalized synchronization: a putative mechanism for implicit learning in neural systems
• Stability and memory-loss go hand-in-hand: three results in dynamics and computation

Cited In (5)

• A robust method for distinguishing between learned and spurious attractors
• Learning Theory for Dynamical Systems
• Data-driven cold starting of good reservoirs
• Learning dynamics by reservoir computing (In Memory of Prof. Pavol Brunovský)
• Generalised synchronisations, embeddings, and approximations for continuous time reservoir computers

This page was built for publication: Learning strange attractors with reservoir systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6169729)