English
Related papers

Related papers: Learning strange attractors with reservoir systems

200 papers

The Hopfield model is a paradigmatic model of neural networks that has been analyzed for many decades in the statistical physics, neuroscience, and machine learning communities. Inspired by the manifold hypothesis in machine learning, we…

Disordered Systems and Neural Networks · Physics 2023-05-01 Matteo Negri , Clarissa Lauditi , Gabriele Perugini , Carlo Lucibello , Enrico Malatesta

This paper concerns the dynamical behavior of weakly reversible, deterministically modeled population processes near the facets (codimension-one faces) of their invariant manifolds and proves that the facets of such systems are "repelling."…

Dynamical Systems · Mathematics 2009-11-25 David F. Anderson , Anne Shiu

Learning, inference, and emergence in biological and artificial systems are often studied within disparate theoretical frameworks, ranging from energy-based models to recurrent and attention-based architectures. Here we develop a unified…

Neurons and Cognition · Quantitative Biology 2026-01-22 Byung Gyu Chae

Forecasting chaotic time series requires models that can capture the intrinsic geometry of the underlying attractor while remaining computationally efficient. We introduce a novel reservoir computing (RC) framework that integrates…

Neural and Evolutionary Computing · Computer Science 2025-11-06 S. K. Laha

How to learn an effective reinforcement learning-based model for control tasks from high-level visual observations is a practical and challenging problem. A key to solving this problem is to learn low-dimensional state representations from…

Machine Learning · Computer Science 2022-12-27 Jianda Chen , Sinno Jialin Pan

A data-driven framework is developed to represent chaotic dynamics on an inertial manifold (IM), and applied to solutions of the Kuramoto-Sivashinsky equation. A hybrid method combining linear and nonlinear (neural-network) dimension…

Machine Learning · Computer Science 2020-06-19 Alec J. Linot , Michael D. Graham

Choosing the optimal observable to model dynamical systems for which we do not know the driving equations is nearly always an ad hoc art. Takens' Delay Embedding Theorem guarantees a diffeomorphism between delay-coordinate vectors built…

Computational Physics · Physics 2026-05-01 Maximilian Topel

The use of Variational Autoencoders in different Machine Learning tasks has drastically increased in the last years. They have been developed as denoising, clustering and generative tools, highlighting a large potential in a wide range of…

Machine Learning · Computer Science 2019-07-12 Helena Andrés-Terré , Pietro Lió

In this article, we investigate the convergence behavior of two classes of gathering protocols with fixed circulant topologies using tools from dynamical systems. Given a fixed number of mobile entities moving in the Euclidean plane, we…

Dynamical Systems · Mathematics 2026-04-15 Raphael Gerlach , Sören von der Gracht , Michael Dellnitz

In dynamical systems saddle points partition the domain into basins of attractions of the remaining locally stable equilibria. This problem is rather common especially in population dynamics models. Precisely, a particular solution of a…

Numerical Analysis · Mathematics 2015-11-26 Roberto Cavoretto , Alessandra De Rossi , Emma Perracchione , Ezio Venturino

Network embedding leverages the node proximity manifested to learn a low-dimensional node vector representation for each node in the network. The learned embeddings could advance various learning tasks such as node classification, network…

Social and Information Networks · Computer Science 2018-08-28 Jundong Li , Harsh Dani , Xia Hu , Jiliang Tang , Yi Chang , Huan Liu

Quantum collision models are receiving increasing attention as they describe many nontrivial phenomena in dynamics of open quantum systems. In a general scenario of both fundamental and practical interest, a quantum system repeatedly…

Quantum Physics · Physics 2022-06-07 Sergey N. Filippov , Ilia A. Luchnikov

Inferring network topology from dynamical observations is a fundamental problem pervading research on complex systems. Here, we present a simple, direct method to infer the structural connection topology of a network, given an observation…

Chaotic Dynamics · Physics 2015-05-19 Srinivas Gorur Shandilya , Marc Timme

A natural way to generalise tensor network variational classes to quantum field systems is via a continuous tensor contraction. This approach is first illustrated for the class of quantum field states known as continuous matrix-product…

Quantum Physics · Physics 2015-08-04 David Jennings , Christoph Brockt , Jutho Haegeman , Tobias J. Osborne , Frank Verstraete

The theory of entanglement provides a fundamentally new language for describing interactions and correlations in many body systems. Its vocabulary consists of qubits and entangled pairs, and the syntax is provided by tensor networks. We…

Quantum Physics · Physics 2021-12-20 Ignacio Cirac , David Perez-Garcia , Norbert Schuch , Frank Verstraete

From the climate system to the effect of the internet on society, chaotic systems appear to have a significant role in our future. Here a method of statistical learning for a class of chaotic systems is described along with underlying…

Applications · Statistics 2020-02-26 Michael LuValle

Concepts from the Ergodic Theory are used to describe the existence of non-transitive maps in attractors of phase synchronous chaotic systems. It is shown that for a class of phase-coherent systems, e.g. the sinusoidally forced Chua's…

Classical Physics · Physics 2015-06-26 M. S. Baptista , T. Pereira , I. L. Caldas , J. C. Sartorelli

Despite the widespread application of recurrent neural networks (RNNs) across a variety of tasks, a unified understanding of how RNNs solve these tasks remains elusive. In particular, it is unclear what dynamical patterns arise in trained…

Machine Learning · Computer Science 2022-06-06 Kyle Aitken , Vinay V. Ramasesh , Ankush Garg , Yuan Cao , David Sussillo , Niru Maheswaranathan

System identification of complex and nonlinear systems is a central problem for model predictive control and model-based reinforcement learning. Despite their complexity, such systems can often be approximated well by a set of linear…

Machine Learning · Statistics 2019-05-30 Philip Becker-Ehmck , Jan Peters , Patrick van der Smagt

A topological dynamical system induces two natural systems, one is on the hyperspace and the other one is on the probability space. The connection among some dynamical properties on the original space and on the induced spaces are…

Dynamical Systems · Mathematics 2014-01-03 Jie Li , Kesong Yan , Xiangdong Ye