English
Related papers

Related papers: Phase Transition Adaptation

200 papers

There is a growing interest in the development of artificial neural networks that are implemented in a physical system. A major challenge in this context is that these networks are difficult to train since training here would require a…

Emerging Technologies · Computer Science 2026-01-22 Michael te Vrugt

Recurrent neural networks are used to forecast time series in finance, climate, language, and from many other domains. Reservoir computers are a particularly easily trainable form of recurrent neural network. Recently, a "next-generation"…

Machine Learning · Computer Science 2023-03-28 Sarah E. Marzen , Paul M. Riechers , James P. Crutchfield

Tasks in which rewards depend upon past information not available in the current observation set can only be solved by agents that are equipped with short-term memory. Usual choices for memory modules include trainable recurrent hidden…

Machine Learning · Computer Science 2024-12-18 Kevin McKee

Reservoir Computing (RC) is a powerful computational paradigm that allows high versatility with cheap learning. While other artificial intelligence approaches need exhaustive resources to specify their inner workings, RC is based on a…

Adaptation and Self-Organizing Systems · Physics 2018-11-26 Luís F Seoane

Reservoir computing (RC), first applied to temporal signal processing, is a recurrent neural network in which neurons are randomly connected. Once initialized, the connection strengths remain unchanged. Such a simple structure turns RC into…

Neural and Evolutionary Computing · Computer Science 2023-08-10 Heng Zhang , Danilo Vasconcellos Vargas

Reservoir computing is a neural network approach for processing time-dependent signals that has seen rapid development in recent years. Physical implementations of the technique using optical reservoirs have demonstrated remarkable accuracy…

Machine Learning · Computer Science 2019-01-30 Daniel Canaday , Aaron Griffith , Daniel Gauthier

Reservoir Computing is a novel computing paradigm which uses a nonlinear recurrent dynamical system to carry out information processing. Recent electronic and optoelectronic Reservoir Computers based on an architecture with a single…

The combination of machine learning and quantum computing has emerged as a promising approach for addressing previously untenable problems. Reservoir computing is an efficient learning paradigm that utilizes nonlinear dynamical systems for…

Quantum Physics · Physics 2020-08-26 Jiayin Chen , Hendra I. Nurdin , Naoki Yamamoto

Deciphering the underpinnings of the dynamical processes leading to information transmission, processing, and storing in the brain is a crucial challenge in neuroscience. An inspiring but speculative theoretical idea is that such dynamics…

Statistical Mechanics · Physics 2023-07-21 Guillermo B. Morales , Serena Di Santo , Miguel A. Muñoz

The goal of Deep Domain Adaptation is to make it possible to use Deep Nets trained in one domain where there is enough annotated training data in another where there is little or none. Most current approaches have focused on learning…

Computer Vision and Pattern Recognition · Computer Science 2017-11-22 Artem Rozantsev , Mathieu Salzmann , Pascal Fua

Dynamical systems are capable of performing computation in a reservoir computing paradigm. This paper presents a general representation of these systems as an artificial neural network (ANN). Initially, we implement the simplest dynamical…

Neural and Evolutionary Computing · Computer Science 2019-07-04 Sidney Pontes-Filho , Anis Yazidi , Jianhua Zhang , Hugo Hammer , Gustavo B. M. Mello , Ioanna Sandvig , Gunnar Tufte , Stefano Nichele

Multifunctionality is a well observed phenomenological feature of biological neural networks and considered to be of fundamental importance to the survival of certain species over time. These multifunctional neural networks are capable of…

Neural and Evolutionary Computing · Computer Science 2021-02-03 Andrew Flynn , Vassilios A. Tsachouridis , Andreas Amann

A new machine learning scheme, termed versatile reservoir computing, is proposed for sustaining the dynamics of heterogeneous complex networks. We show that a single, small-scale reservoir computer trained on time series from a subset of…

Chaotic Dynamics · Physics 2025-05-22 Yao Du , Huawei Fan , Xingang Wang

Reservoir computing (RC) is a state-of-the-art machine learning method that makes use of the power of dynamical systems (the reservoir) for real-time inference. When using biological complex systems as reservoir substrates, it serves as a…

Adaptation and Self-Organizing Systems · Physics 2026-03-03 Mario U. Gaimann , Miriam Klopotek

We propose and demonstrate a nonlinear control method that can be applied to unknown, complex systems where the controller is based on a type of artificial neural network known as a reservoir computer. In contrast to many modern…

Systems and Control · Electrical Eng. & Systems 2020-10-07 Daniel Canaday , Andrew Pomerance , Daniel J Gauthier

Reservoir computing is a machine learning approach that can generate a surrogate model of a dynamical system. It can learn the underlying dynamical system using fewer trainable parameters and hence smaller training data sets than competing…

Machine Learning · Computer Science 2022-11-23 Daniel J. Gauthier , Ingo Fischer , André Röhm

Physical reservoir computing is a computational framework that offers an energy- and computation-efficient alternative to conventional training of neural networks. In reservoir computing, input signals are mapped into the high-dimensional…

Soft Condensed Matter · Physics 2026-01-12 Veit-Lorenz Heuthe , Lukas Seemann , Samuel Tovey , Clemens Bechinger

The paper presents a novel, principled approach to train recurrent neural networks from the Reservoir Computing family that are robust to missing part of the input features at prediction time. By building on the ensembling properties of…

Machine Learning · Computer Science 2017-05-09 Davide Bacciu , Francesco Crecchi , Davide Morelli

We demonstrate a data-driven technique for adaptive control in dynamical systems that exploits the reservoir computing method. We show that a reservoir computer can be trained to predict a system parameter from the time series data.…

In nonlinear dynamical systems, tipping refers to a critical transition from one steady state to another, typically catastrophic, steady state, often resulting from a saddle-node bifurcation. Recently, the machine-learning framework of…

Chaotic Dynamics · Physics 2026-04-09 Smita Deb , Zheng-Meng Zhai , Mulugeta Haile , Ying-Cheng Lai