English
Related papers

Related papers: On Dominant Manifolds in Reservoir Computing Netwo…

200 papers

Reservoir computing typically relies on large, randomly generated reservoirs, enabling simple, often linear readouts. Over the past two decades, most constructions have exploited the freedom to select the reservoir, constrained primarily by…

Dynamical Systems · Mathematics 2026-05-26 G Manjunath , Juan-Pablo Ortega , Alma van der Merwe

A common difficulty in applications of machine learning is the lack of any general principle for guiding the choices of key parameters of the underlying neural network. Focusing on a class of recurrent neural networks - reservoir computing…

Machine Learning · Computer Science 2019-10-11 Junjie Jiang , Ying-Cheng Lai

In this work, we give a characterization of the reservoir computer (RC) by the network structure, especially the probability distribution of random coupling constants. First, based on the path integral method, we clarify the universal…

Disordered Systems and Neural Networks · Physics 2023-02-28 Junichi Haruna , Riki Toshio , Naoto Nakano

Recent empirical evidence has demonstrated that the training dynamics of large-scale deep neural networks occur within low-dimensional subspaces. While this has inspired new research into low-rank training, compression, and adaptation,…

Machine Learning · Computer Science 2026-02-09 Alec S. Xu , Can Yaras , Matthew Asato , Qing Qu , Laura Balzano

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

Complex chaotic dynamics, seen in natural and industrial systems like turbulent flows and weather patterns, often span vast spatial domains with interactions across scales. Accurately capturing these features requires a high-dimensional…

Chaotic Dynamics · Physics 2024-10-03 C. Ricardo Constante-Amores , Alec J. Linot , Michael D. Graham

Randomized Neural Networks explore the behavior of neural systems where the majority of connections are fixed, either in a stochastic or a deterministic fashion. Typical examples of such systems consist of multi-layered neural network…

Machine Learning · Computer Science 2021-02-03 Claudio Gallicchio , Simone Scardapane

Forecasting high-dimensional spatiotemporal systems remains computationally challenging for recurrent neural networks (RNNs) and long short-term memory (LSTM) models due to gradient-based training and memory bottlenecks. Reservoir Computing…

Machine Learning · Computer Science 2026-01-05 Ata Akbari Asanjan , Filip Wudarski , Daniel O'Connor , Shaun Geaney , Elena Strbac , P. Aaron Lott , Davide Venturelli

Cortical networks are strongly recurrent, and neurons have intrinsic temporal dynamics. This sets them apart from deep feed-forward networks. Despite the tremendous progress in the application of feed-forward networks and their theoretical…

Disordered Systems and Neural Networks · Physics 2021-07-14 Sandra Nestler , Christian Keup , David Dahmen , Matthieu Gilson , Holger Rauhut , Moritz Helias

A fundamental feature of complex biological systems is the ability to form feedback interactions with their environment. A prominent model for studying such interactions is reservoir computing, where learning acts on low-dimensional…

Neurons and Cognition · Quantitative Biology 2021-03-03 Lee Susman , Francesca Mastrogiuseppe , Naama Brenner , Omri Barak

We examine the efficiency of Recurrent Neural Networks in forecasting the spatiotemporal dynamics of high dimensional and reduced order complex systems using Reservoir Computing (RC) and Backpropagation through time (BPTT) for gated network…

Signal Processing · Electrical Eng. & Systems 2020-02-19 Pantelis R. Vlachas , Jaideep Pathak , Brian R. Hunt , Themistoklis P. Sapsis , Michelle Girvan , Edward Ott , Petros Koumoutsakos

Reservoir Computing (RC) refers to a Recurrent Neural Networks (RNNs) framework, frequently used for sequence learning and time series prediction. The RC system consists of a random fixed-weight RNN (the input-hidden reservoir layer) and a…

Machine Learning · Computer Science 2017-06-27 M. Andrecut

Reservoir Computing (RC), a type of recurrent random neural network, is a powerful framework for modeling complex and chaotic dynamics. However, its autonomous (closed-loop) operation is often plagued by inherent instability. Moreover,…

Chaotic Dynamics · Physics 2026-02-12 Satoshi Oishi , Hiroshi Yamashita , Hideyuki Suzuki , Sho Shirasaka

Reservoir computing is a recently introduced machine learning paradigm that has been shown to be well-suited for the processing of spatiotemporal data. Rather than training the network node connections and weights via backpropagation in…

Neural and Evolutionary Computing · Computer Science 2016-07-20 Ashley Prater

Reservoir Computing offers a great computational framework where a physical system can directly be used as computational substrate. Typically a "reservoir" is comprised of a large number of dynamical systems, and is consequently…

Chaotic Dynamics · Physics 2022-05-11 Swarnendu Mandal , Sudeshna Sinha , Manish Dev Shrimali

We present an Auto-Encoded Reservoir-Computing (AE-RC) approach to learn the dynamics of a 2D turbulent flow. The AE-RC consists of an Autoencoder, which discovers an efficient manifold representation of the flow state, and an Echo State…

Fluid Dynamics · Physics 2021-03-25 Nguyen Anh Khoa Doan , Wolfgang Polifke , Luca Magri

Recently, studies on deep Reservoir Computing (RC) highlighted the role of layering in deep recurrent neural networks (RNNs). In this paper, the use of linear recurrent units allows us to bring more evidence on the intrinsic hierarchical…

Machine Learning · Computer Science 2017-07-11 Claudio Gallicchio , Alessio Micheli , Luca Pedrelli

Reservoirs, typically implemented as recurrent neural networks with fixed random connection weights, can be combined with a simple trained readout layer to perform a wide range of computational tasks. However, increasing the magnitude of…

Neurons and Cognition · Quantitative Biology 2026-04-01 Claus Metzner , Achim Schilling , Andreas Maier , Thomas Kinfe , Patrick Krauss

Recurrent neural networks (RNNs) provide a theoretical framework for understanding computation in biological neural circuits, yet classical results, such as Hopfield's model of associative memory, rely on symmetric connectivity that…

Disordered Systems and Neural Networks · Physics 2026-02-17 Ramón Nartallo-Kaluarachchi , Renaud Lambiotte , Alain Goriely

Deep generative networks have been widely used for learning mappings from a low-dimensional latent space to a high-dimensional data space. In many cases, data transformations are defined by linear paths in this latent space. However, the…

Machine Learning · Statistics 2019-12-06 Marissa Connor , Christopher Rozell