☆ 4.7 Article

Learn one size to infer all: Exploiting translational symmetries in delay-dynamical and spatiotemporal systems using scalable neural networks

PHYSICAL REVIEW E (2022)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Physics, Multidisciplinary

Parallel Machine Learning for Forecasting the Dynamics of Complex Networks

Keshav Srinivasan et al.

Summary: Forecasting the dynamics of large, complex, sparse networks is crucial in various contexts. In this study, a machine learning scheme is proposed that utilizes a parallel architecture mirroring the topology of the network of interest. The method, implemented using reservoir computing on a chaotic network of oscillators, demonstrates its utility and scalability. Two levels of prior knowledge are considered: known network links and network links inferred through data-driven optimization.

PHYSICAL REVIEW LETTERS (2022)

添加到收藏夹

Article Physics, Multidisciplinary

Machine Learning Hidden Symmetries

Ziming Liu et al.

Summary: This automated method can find hidden symmetries by quantifying asymmetry and numerically optimizing to minimize violation in all invertible transformations. It has rediscovered hidden symmetries like the Gullstrand-Painlevé metric.

PHYSICAL REVIEW LETTERS (2022)

添加到收藏夹

Article Mathematics, Applied

Learning spatiotemporal chaos using next-generation reservoir computing

Wendson A. S. Barbosa et al.

Summary: Forecasting the behavior of high-dimensional dynamical systems using machine learning requires efficient methods to learn the underlying physical model. This study demonstrates spatiotemporal chaos prediction using a machine learning architecture combined with a next-generation reservoir computer, which achieves state-of-the-art performance with significantly faster training process and smaller training data set compared to other machine learning algorithms. The computational cost and training data are further reduced by exploiting the translational symmetry of the model.

CHAOS (2022)

添加到收藏夹

Article Mathematics, Applied

Model-free inference of unseen attractors: Reconstructing phase space features from a single noisy trajectory using reservoir computing

Andre Rohm et al.

Summary: Reservoir computers are powerful tools for chaotic time series prediction and can infer the dynamics of systems with multiple co-existing attractors. Through proper training, reservoir computers can predict unexplored attractors and achieve attractor inference on single noisy trajectories.

CHAOS (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Biologically informed deep neural network for prostate cancer discovery

Haitham A. Elmarakeby et al.

Summary: The development of a biologically informed deep learning model P-NET enables stratification of prostate cancer patients by treatment-resistance state and evaluation of molecular drivers of treatment resistance for therapeutic targeting with complete model interpretability. This approach shows superior performance in cancer state prediction using molecular data compared to other modeling approaches.

NATURE (2021)

添加到收藏夹

Article Optics

Time delay estimation from the time series for optical chaos systems using deep learning

Xiaojing Gao et al.

Summary: A model-free time delay signature (TDS) extraction method for optical chaos systems has been proposed. The blind identification method based on long short-term memory neural network (LSTM-NN) model shows effectiveness in extracting TDS in chaos systems with high tolerance to additive noise.

OPTICS EXPRESS (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Next generation reservoir computing

Daniel J. Gauthier et al.

Summary: Reservoir computers are artificial neural networks that can be trained on small data sets with large random matrices and numerous metaparameters. Nonlinear vector autoregression is a superior machine learning algorithm compared to reservoir computing, requiring fewer training data sets and training time.

NATURE COMMUNICATIONS (2021)

添加到收藏夹

Article Physics, Fluids & Plasmas

Symmetry-aware reservoir computing

Wendson A. S. Barbosa et al.

Summary: Matching the symmetry properties of a reservoir computer to the data being processed significantly increases its processing power, as demonstrated in this study. The method is particularly effective for tasks such as parity and chaotic system inference, where symmetry plays a key role. By respecting and leveraging symmetries, the network size required for zero error classification scales linearly with the task complexity, showcasing the potential for exponential reductions in training data size and improved performance.

PHYSICAL REVIEW E (2021)

添加到收藏夹

Article Mathematics, Interdisciplinary Applications

Emergence of transient chaos and intermittency in machine learning

Ling-Wei Kong et al.

Summary: Machine learning with reservoir computing is a promising approach for predicting the state evolution of chaotic systems, with recent developments showing success in predicting system collapse and chaotic transients. By adding a parameter channel to reservoir computing, accurate predictions of crisis points after transient chaos emergence can be made. Additionally, this framework can reproduce intermittency of the target system and solve problems that traditional methods of sparse optimization fail to address.

JOURNAL OF PHYSICS-COMPLEXITY (2021)

添加到收藏夹

Review Physics, Applied

Physics-informed machine learning

George Em Karniadakis et al.

Summary: Physics-informed learning seamlessly integrates data and mathematical models through neural networks or kernel-based regression networks for accurate inference of realistic and high-dimensional multiphysics problems. Challenges remain in incorporating noisy data seamlessly, complex mesh generation, and addressing high-dimensional problems.

NATURE REVIEWS PHYSICS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Teaching recurrent neural networks to infer global temporal structure from local examples

Jason Z. Kim et al.

Summary: Computational systems are designed to store and manipulate information, while neurobiological systems adapt to perform similar functions without explicit engineering. Recent research has shown that recurrent neural networks (RNNs) can learn to modify complex information representations using examples and control signals, allowing for continuous interpolation and extrapolation of these representations far beyond the training data. Furthermore, RNNs can infer bifurcation structures and chaos routes, as well as extrapolate non-dynamical trajectories.

NATURE MACHINE INTELLIGENCE (2021)

添加到收藏夹

Article Physics, Multidisciplinary

Machine learning prediction of critical transition and system collapse

Ling-Wei Kong et al.

Summary: This study presents a model-free solution based on machine learning and reservoir computing for predicting critical transitions caused by parameter drift and the transient state of a system before its collapse. The accuracy of this method reveals important physical properties of transient chaos.

PHYSICAL REVIEW RESEARCH (2021)

添加到收藏夹

Article Mathematics, Applied

Introduction to Focus Issue: When machine learning meets complex systems: Networks, chaos, and nonlinear dynamics

Yang Tang et al.

CHAOS (2020)

添加到收藏夹

Article Physics, Multidisciplinary

Dynamical Learning of Dynamics

Christian Klos et al.

PHYSICAL REVIEW LETTERS (2020)

添加到收藏夹

Article Mathematics, Applied

Detecting unstable periodic orbits based only on time series: When adaptive delayed feedback control meets reservoir computing

Qunxi Zhu et al.

CHAOS (2019)

添加到收藏夹

Article Physics, Applied

Constructive Role of Noise for High-Quality Replication of Chaotic Attractor Dynamics Using a Hardware-Based Reservoir Computer

Irene Estebanez et al.

PHYSICAL REVIEW APPLIED (2019)

添加到收藏夹

Article Mathematics, Applied

Good and bad predictions: Assessing and improving the replication of chaotic attractors by means of reservoir computing

Alexander Haluszczynski et al.

CHAOS (2019)

添加到收藏夹

Review Physics, Multidisciplinary

The Application of Machine Learning Techniques to Improve El Nino Prediction Skill

Henk A. Dijkstra et al.

FRONTIERS IN PHYSICS (2019)

添加到收藏夹

Review Health Care Sciences & Services

Integrating machine learning and multiscale modeling-perspectives, challenges, and opportunities in the biologica biomedical, and behavioral sciences

Mark Alber et al.

NPJ DIGITAL MEDICINE (2019)

添加到收藏夹

Article Mathematics, Applied

Attractor reconstruction by machine learning

Zhixin Lu et al.

CHAOS (2018)

添加到收藏夹

Article Physics, Multidisciplinary

Model-Free Prediction of Large Spatiotemporally Chaotic Systems from Data: A Reservoir Computing Approach

Jaideep Pathak et al.

PHYSICAL REVIEW LETTERS (2018)

添加到收藏夹

Article Physics, Fluids & Plasmas

Using a reservoir computer to learn chaotic attractors, with applications to chaos synchronization and cryptography

Piotr Antonik et al.

PHYSICAL REVIEW E (2018)

添加到收藏夹

Article Mathematics, Applied

Chimera states in multi-strain epidemic models with temporary immunity

Larissa Bauer et al.

CHAOS (2017)

添加到收藏夹

Article Mathematics, Applied

Oscillatory dynamics of an intravenous glucose tolerance test model with delay interval

Xiangyun Shi et al.

CHAOS (2017)

添加到收藏夹

Article Mathematics, Applied

Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data

Jaideep Pathak et al.

CHAOS (2017)

添加到收藏夹

Article Mathematics, Applied

Climate models with delay differential equations

Andrew Keane et al.

CHAOS (2017)

添加到收藏夹

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

添加到收藏夹

Article Physics, Multidisciplinary

Virtual Chimera States for Delayed-Feedback Systems

Laurent Larger et al.

PHYSICAL REVIEW LETTERS (2013)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Reservoir Computing Trends

Mantas Lukosevicius et al.

KUNSTLICHE INTELLIGENZ (2012)

添加到收藏夹

Article Physics, Multidisciplinary

Strong and Weak Chaos in Nonlinear Networks with Time-Delayed Couplings

Sven Heiligenthal et al.

PHYSICAL REVIEW LETTERS (2011)

添加到收藏夹

Article Multidisciplinary Sciences

Information processing using a single dynamical node as complex system

L. Appeltant et al.

NATURE COMMUNICATIONS (2011)

添加到收藏夹

Article Multidisciplinary Sciences

Traffic jams: dynamics and control INTRODUCTION

Gabor Orosz et al.

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES (2010)

添加到收藏夹

Article Multidisciplinary Sciences

Delay effects in the human sensory system during balancing

Gabor Stepan

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES (2009)

添加到收藏夹

Article Multidisciplinary Sciences

Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication

H Jaeger et al.

SCIENCE (2004)

添加到收藏夹

Article Mathematics, Applied

Ikeda Hopf bifurcation revisited

T Erneux et al.

PHYSICA D-NONLINEAR PHENOMENA (2004)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Real-time computing without stable states:: A new framework for neural computation based on perturbations

W Maass et al.

NEURAL COMPUTATION (2002)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.