English
Related papers

Related papers: Automatic-differentiated Physics-Informed Echo Sta…

200 papers

Echo State Networks (ESNs) are simplified recurrent neural network models composed of a reservoir and a linear, trainable readout layer. The reservoir is tunable by some hyper-parameters that control the network behaviour. ESNs are known to…

Neural and Evolutionary Computing · Computer Science 2018-11-06 Pietro Verzelli , Lorenzo Livi , Cesare Alippi

The study of deep recurrent neural networks (RNNs) and, in particular, of deep Reservoir Computing (RC) is gaining an increasing research attention in the neural networks community. The recently introduced Deep Echo State Network (DeepESN)…

Machine Learning · Computer Science 2020-09-28 Claudio Gallicchio , Alessio Micheli

The spatiotemporal dynamics of turbulent flows is chaotic and difficult to predict. This makes the design of accurate and stable reduced-order models challenging. The overarching objective of this paper is to propose a nonlinear…

Fluid Dynamics · Physics 2022-11-23 Alberto Racca , Nguyen Anh Khoa Doan , Luca Magri

Echo state networks are computationally lightweight reservoir models inspired by the random projections observed in cortical circuitry. As interest in reservoir computing has grown, networks have become deeper and more intricate. While…

Signal Processing · Electrical Eng. & Systems 2019-08-23 Zachariah Carmichael , Humza Syed , Dhireesha Kudithipudi

This paper investigates the performance of Echo State Networks (ESNs) for univariate time series forecasting using a subset of the M4 Forecasting Competition dataset. Focusing on monthly and quarterly time series, we evaluate whether a…

Machine Learning · Computer Science 2026-04-08 Alexander Häußer

We present a data-driven model to reconstruct nonlinear dynamics from a very sparse times series data, which relies on the strength of the echo state network (ESN) in learning nonlinear representation of data. With an assumption of the…

Neural and Evolutionary Computing · Computer Science 2019-07-24 Kyongmin Yeo

This paper presents a method for reproducing a simple central pattern generator (CPG) using a modified Echo State Network (ESN). Conventionally, the dynamical reservoir needs to be damped to stabilize and preserve memory. However, we find…

Neural and Evolutionary Computing · Computer Science 2023-06-21 Tham Yik Foong , Danilo Vasconcellos Vargas

We propose Echo State Networks (ESNs) to predict the statistics of extreme events in a turbulent flow. We train the ESNs on small datasets that lack information about the extreme events. We asses whether the networks are able to extrapolate…

Fluid Dynamics · Physics 2022-04-13 Alberto Racca , Luca Magri

The performance of automatic speech recognition (ASR) has improved tremendously due to the application of deep neural networks (DNNs). Despite this progress, building a new ASR system remains a challenging task, requiring various resources,…

Computation and Language · Computer Science 2015-10-20 Yajie Miao , Mohammad Gowayyed , Florian Metze

We developed a new class of physics-informed generative adversarial networks (PI-GANs) to solve in a unified manner forward, inverse and mixed stochastic problems based on a limited number of scattered measurements. Unlike standard GANs…

Machine Learning · Statistics 2018-11-07 Liu Yang , Dongkun Zhang , George Em Karniadakis

We propose a new class of physics-informed neural networks, called Physics-Informed Generator-Encoder Adversarial Networks, to effectively address the challenges posed by forward, inverse, and mixed problems in stochastic differential…

Machine Learning · Computer Science 2023-11-06 Ruisong Gao , Min Yang , Jin Zhang

We develop a versatile optimization method, which finds the design parameters that minimize time-averaged acoustic cost functionals. The method is gradient-free, model-informed, and data-driven with reservoir computing based on echo state…

Fluid Dynamics · Physics 2022-02-03 Francisco Huhn , Luca Magri

In this paper, we explore the predictive capabilities of echo state networks (ESNs) for the generalized Kuramoto-Sivashinsky (gKS) equation, an archetypal nonlinear PDE that exhibits spatiotemporal chaos. Our research focuses on predicting…

Dynamical Systems · Mathematics 2025-12-23 Mohammad Shah Alam , William Ott , Ilya Timofeyev

Inspired by the numerical solution of ordinary differential equations, in this paper we propose a novel Reservoir Computing (RC) model, called the Euler State Network (EuSN). The presented approach makes use of forward Euler discretization…

Machine Learning · Computer Science 2023-03-27 Claudio Gallicchio

Physics-informed neural networks (PINNs) are trained using physical equations and can also incorporate unmodeled effects by learning from data. PINNs for control (PINCs) of dynamical systems are gaining interest due to their prediction…

Systems and Control · Electrical Eng. & Systems 2024-08-29 Henrik Krauss , Tim-Lukas Habich , Max Bartholdt , Thomas Seel , Moritz Schappler

We propose a continuous neural network architecture, termed Explainable Tensorized Neural Ordinary Differential Equations (ETN-ODE), for multi-step time series prediction at arbitrary time points. Unlike the existing approaches, which…

Machine Learning · Computer Science 2022-07-13 Penglei Gao , Xi Yang , Rui Zhang , Kaizhu Huang

Echo-State Networks and Reservoir Computing have been studied for more than a decade. They provide a simpler yet powerful alternative to Recurrent Neural Networks, every internal weight is fixed and only the last linear layer is trained.…

Emerging Technologies · Computer Science 2018-09-25 Jonathan Dong , Sylvain Gigan , Florent Krzakala , Gilles Wainrib

Echo State Networks (ESNs) are widely-used Recurrent Neural Networks. They are dynamical systems including, in state-space form, a nonlinear state equation and a linear output transformation. The common procedure to train ESNs is to…

Systems and Control · Electrical Eng. & Systems 2019-12-05 Luca Bugliari Armenio , Lorenzo Fagiano , Enrico Terzi , Marcello Farina , Riccardo Scattolini

Partial differential equations, and their chaotic solutions, are pervasive in the modelling of complex systems in engineering, science, and beyond. Data-driven methods can find solutions to partial differential equations with a…

Chaotic Dynamics · Physics 2024-10-02 Elise Özalp , Luca Magri

Time series forecasting often demands a trade-off between accuracy and efficiency. While recent Transformer models have improved forecasting capabilities, they come with high computational costs. Linear-based models have shown better…

Machine Learning · Computer Science 2025-07-14 Ahmad Mohammadshirazi , Pinaki Prasad Guha Neogi , Rajiv Ramnath
‹ Prev 1 3 4 5 6 7 10 Next ›