English
Related papers

Related papers: Stochastic dynamics learning with state-space syst…

200 papers

Reservoir Computing (RC) provides an efficient way for designing dynamical recurrent neural models. While training is restricted to a simple output component, the recurrent connections are left untrained after initialization, subject to…

Neural and Evolutionary Computing · Computer Science 2019-09-25 Claudio Gallicchio

Reservoir computing (RC) represents a class of state-space models (SSMs) characterized by a fixed state transition mechanism (the reservoir) and a flexible readout layer that maps from the state space. It is a paradigm of computational…

Machine Learning · Computer Science 2025-04-17 Pradeep Singh , Ashutosh Kumar , Sutirtha Ghosh , Hrishit B P , Balasubramanian Raman

A reservoir computer is a special type of neural network, where most of the weights are randomly fixed and only a subset are trained. In this thesis we prove results about reservoir computers trained on deterministic dynamical systems, and…

Dynamical Systems · Mathematics 2021-12-28 Allen G Hart

Reservoir computing is a form of machine learning that utilizes nonlinear dynamical systems to perform complex tasks in a cost-effective manner when compared to typical neural networks. Many recent advancements in reservoir computing, in…

Machine Learning · Computer Science 2025-04-03 Peter J. Ehlers , Hendra I. Nurdin , Daniel Soh

The echo state property (ESP) represents a fundamental concept in the reservoir computing (RC) framework that ensures output-only training of reservoir networks by being agnostic to the initial states and far past inputs. However, the…

Quantum Physics · Physics 2024-09-04 Shumpei Kobayashi , Quoc Hoan Tran , Kohei Nakajima

A probabilistic framework to study the dependence structure induced by deterministic discrete-time state-space systems between input and output processes is introduced. General sufficient conditions are formulated under which output…

Machine Learning · Statistics 2025-03-13 Juan-Pablo Ortega , Florian Rossmannek

We study data-driven learning of robust stochastic control for infinite-horizon systems with potentially continuous state and action spaces. In many managerial settings--supply chains, finance, manufacturing, services, and dynamic…

Machine Learning · Statistics 2025-11-18 Shengbo Wang , Jason Meng , Nian Si , Jose Blanchet , Zhengyuan Zhou

This paper extends the notion of information processing capacity for non-independent input signals in the context of reservoir computing (RC). The presence of input autocorrelation makes worthwhile the treatment of forecasting and filtering…

Emerging Technologies · Computer Science 2015-10-08 Lyudmila Grigoryeva , Julie Henriques , Juan-Pablo Ortega

Echo-State Networks (ESNs) distil a key neurobiological insight: richly recurrent but fixed circuitry combined with adaptive linear read-outs can transform temporal streams with remarkable efficiency. Yet fundamental questions about…

Neural and Evolutionary Computing · Computer Science 2025-07-25 Pradeep Singh , Lavanya Sankaranarayanan , Balasubramanian Raman

Machine learning techniques offer an effective approach to modeling dynamical systems solely from observed data. However, without explicit structural priors -- built-in assumptions about the underlying dynamics -- these techniques typically…

Machine Learning · Computer Science 2025-10-30 Declan A. Norton , Yuanzhao Zhang , Michelle Girvan

We consider the general class of time-homogeneous stochastic dynamical systems, both discrete and continuous, and study the problem of learning a representation of the state that faithfully captures its dynamics. This is instrumental to…

Machine Learning · Computer Science 2024-03-15 Vladimir R. Kostic , Pietro Novelli , Riccardo Grazzi , Karim Lounici , Massimiliano Pontil

Stochastic systems with memory naturally appear in life science, economy, and finance. We take the modelling point of view of stochastic functional delay equations and we study these structures when the driving noises admit jumps. Our…

Probability · Mathematics 2016-06-01 D. R. Baños , F. Cordoni , G. Di Nunno , L. Di Persio , E. E. Røse

Parameterized state space models in the form of recurrent networks are often used in machine learning to learn from data streams exhibiting temporal dependencies. To break the black box nature of such models it is important to understand…

Machine Learning · Computer Science 2020-02-18 Peter Tino

Machine learning methods have shown promise in learning chaotic dynamical systems, enabling model-free short-term prediction and attractor reconstruction. However, when applied to large-scale, spatiotemporally chaotic systems, purely…

Chaotic Dynamics · Physics 2026-01-09 Kuei-Jan Chu , Nozomi Akashi , Akihiro Yamamoto

The prediction of stochastic dynamical systems and the capture of dynamical behaviors are profound problems. In this article, we propose a data-driven framework combining Reservoir Computing and Normalizing Flow to study this issue, which…

Dynamical Systems · Mathematics 2023-08-01 Cheng Fang , Yubin Lu , Ting Gao , Jinqiao Duan

Learning tractable linear representations of nonlinear dynamical systems via Koopman operator theory is often hindered by dictionary selection, temporal memory encoding, and numerical ill-conditioning. Inspired by Reservoir Computing (RC)…

Machine Learning · Computer Science 2026-05-07 Weibin Gu , Chen Yang , Lu Shi

Much effort has been devoted in the last two decades to characterize the situations in which a reservoir computing system exhibits the so-called echo state (ESP) and fading memory (FMP) properties. These important features amount, in…

Neural and Evolutionary Computing · Computer Science 2019-03-25 Lyudmila Grigoryeva , Juan-Pablo Ortega

Reservoir Computing (RC) is a popular methodology for the efficient design of Recurrent Neural Networks (RNNs). Recently, the advantages of the RC approach have been extended to the context of multi-layered RNNs, with the introduction of…

Machine Learning · Computer Science 2019-09-25 Claudio Gallicchio , Alessio Micheli

We are interested in understanding stability (almost sure boundedness) of stochastic approximation algorithms (SAs) driven by a `controlled Markov' process. Analyzing this class of algorithms is important, since many reinforcement learning…

Systems and Control · Computer Science 2018-05-18 Arunselvan Ramaswamy , Shalabh Bhatnagar

Reservoir computing systems are constructed using a driven dynamical system in which external inputs can alter the evolving states of a system. These paradigms are used in information processing, machine learning, and computation. A…

Neural and Evolutionary Computing · Computer Science 2023-04-26 G Manjunath , Juan-Pablo Ortega
‹ Prev 1 2 3 10 Next ›