Log in

Relevant bibliographies by topics / Reservoir computing / Journal articles

To see the other types of publications on this topic, follow the link: Reservoir computing.

Journal articles on the topic 'Reservoir computing'

Author: Grafiati

Published: 4 June 2021

Last updated: 15 February 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 journal articles for your research on the topic 'Reservoir computing.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.

1

Van der Sande, Guy, Daniel Brunner, and Miguel C. Soriano. "Advances in photonic reservoir computing." Nanophotonics 6, no. 3 (May 12, 2017): 561–76. http://dx.doi.org/10.1515/nanoph-2016-0132.

Full text

Abstract:

AbstractWe review a novel paradigm that has emerged in analogue neuromorphic optical computing. The goal is to implement a reservoir computer in optics, where information is encoded in the intensity and phase of the optical field. Reservoir computing is a bio-inspired approach especially suited for processing time-dependent information. The reservoir’s complex and high-dimensional transient response to the input signal is capable of universal computation. The reservoir does not need to be trained, which makes it very well suited for optics. As such, much of the promise of photonic reservoirs lies in their minimal hardware requirements, a tremendous advantage over other hardware-intensive neural network models. We review the two main approaches to optical reservoir computing: networks implemented with multiple discrete optical nodes and the continuous system of a single nonlinear device coupled to delayed feedback.

APA, Harvard, Vancouver, ISO, and other styles

2

Tanaka, Gouhei. "Reservoir Computing." Journal of The Institute of Image Information and Television Engineers 74, no. 3 (2020): 532–34. http://dx.doi.org/10.3169/itej.74.532.

Full text

APA, Harvard, Vancouver, ISO, and other styles

3

Antonik, Piotr, Serge Massar, and Guy Van Der Sande. "Photonic reservoir computing using delay dynamical systems." Photoniques, no. 104 (September 2020): 45–48. http://dx.doi.org/10.1051/photon/202010445.

Full text

Abstract:

The recent progress in artificial intelligence has spurred renewed interest in hardware implementations of neural networks. Reservoir computing is a powerful, highly versatile machine learning algorithm well suited for experimental implementations. The simplest highperformance architecture is based on delay dynamical systems. We illustrate its power through a series of photonic examples, including the first all optical reservoir computer and reservoir computers based on lasers with delayed feedback. We also show how reservoirs can be used to emulate dynamical systems. We discuss the perspectives of photonic reservoir computing.

APA, Harvard, Vancouver, ISO, and other styles

4

Senn, Christoph Walter, and Itsuo Kumazawa. "Abstract Reservoir Computing." AI 3, no. 1 (March 10, 2022): 194–210. http://dx.doi.org/10.3390/ai3010012.

Full text

Abstract:

Noise of any kind can be an issue when translating results from simulations to the real world. We suddenly have to deal with building tolerances, faulty sensors, or just noisy sensor readings. This is especially evident in systems with many free parameters, such as the ones used in physical reservoir computing. By abstracting away these kinds of noise sources using intervals, we derive a regularized training regime for reservoir computing using sets of possible reservoir states. Numerical simulations are used to show the effectiveness of our approach against different sources of errors that can appear in real-world scenarios and compare them with standard approaches. Our results support the application of interval arithmetics to improve the robustness of mass-spring networks trained in simulations.

APA, Harvard, Vancouver, ISO, and other styles

5

Lukoševičius, Mantas, Herbert Jaeger, and Benjamin Schrauwen. "Reservoir Computing Trends." KI - Künstliche Intelligenz 26, no. 4 (May 16, 2012): 365–71. http://dx.doi.org/10.1007/s13218-012-0204-5.

Full text

APA, Harvard, Vancouver, ISO, and other styles

6

NAITOH, Yasuhisa, and Yoshiyuki YAMASHITA. "Physical Reservoir Computing." Vacuum and Surface Science 67, no. 11 (November 10, 2024): 520. http://dx.doi.org/10.1380/vss.67.520.

Full text

APA, Harvard, Vancouver, ISO, and other styles

7

Yue, Dianzuo, Yushuang Hou, Chunxia Hu, Cunru Zang, and Yingzhe Kou. "Handwritten Digits Recognition Based on a Parallel Optoelectronic Time-Delay Reservoir Computing System." Photonics 10, no. 3 (February 22, 2023): 236. http://dx.doi.org/10.3390/photonics10030236.

Full text

Abstract:

In this work, the performance of an optoelectronic time-delay reservoir computing system for performing a handwritten digit recognition task is numerically investigated, and a scheme to improve the recognition speed using multiple parallel reservoirs is proposed. By comparing four image injection methods based on a single time-delay reservoir, we find that when injecting the histograms of oriented gradient (HOG) features of the digit image, the accuracy rate (AR) is relatively high and is less affected by the offset phase. To improve the recognition speed, we construct a parallel time-delay reservoir system including multi-reservoirs, where each reservoir processes part of the HOG features of one image. Based on 6 parallel reservoirs with each reservoir possessing 100 virtual nodes, the AR can reach about 97.8%, and the reservoir processing speed can reach about 1 × 106 digits per second. Meanwhile, the parallel reservoir system shows strong robustness to the parameter mismatch between multi-reservoirs.

APA, Harvard, Vancouver, ISO, and other styles

8

Asadullah, M., P. Behrenbruch, and S. Pham. "RESERVOIR SIMULATION—UPSCALING, STREAMLINES AND PARALLEL COMPUTING." APPEA Journal 47, no. 1 (2007): 199. http://dx.doi.org/10.1071/aj06013.

Full text

Abstract:

Simulation of petroleum reservoirs is becoming more and more complex due to increasing necessity to model heterogeneity of reservoirs for accurate reservoir performance prediction. With high oil prices and less easy oil, accurate reservoir management tools such as simulation models are in more demand than ever before. The aim is to capture and preserve reservoir heterogeneity when changing over from a detailed geocellular model to a flow simulation model, minimising errors when upscaling and preventing excessive numerical dispersion by employing variable and innovative grids, as well as improved computational algorithms.For accurate and efficient simulation of large-scale models there are essentially three choices: upscaling, which involves averaging of parameters for several blocks, resulting in a coarser model that executes faster; the use of streamline simulation, which uses a more optimal grid, combined with a different computational algorithm for increased efficiency; and, the use of parallel computing techniques, which use superior hardware configurations for efficiency gains. With uncertainty screening of various multiple geostatistical realisations and investigation of alternative development scenarios— now commonplace for determining reservoir performance—computational efficiency and accuracy in modelling are paramount. This paper summarises the main techniques and methodologies involved in considering geocellular models for flow simulation of reservoirs, commenting on advantages and disadvantages among the various possibilities. Starting with some historic comments, the three modes of simulation are reviewed and examples are given for illustrative purposes, including a case history for the Bayu-Undan Field, Timor Sea.

APA, Harvard, Vancouver, ISO, and other styles

9

Govia, L. C. G., G. J. Ribeill, G. E. Rowlands, and T. A. Ohki. "Nonlinear input transformations are ubiquitous in quantum reservoir computing." Neuromorphic Computing and Engineering 2, no. 1 (February 18, 2022): 014008. http://dx.doi.org/10.1088/2634-4386/ac4fcd.

Full text

Abstract:

Abstract The nascent computational paradigm of quantum reservoir computing presents an attractive use of near-term, noisy-intermediate-scale quantum processors. To understand the potential power and use cases of quantum reservoir computing, it is necessary to define a conceptual framework to separate its constituent components and determine their impacts on performance. In this manuscript, we utilize such a framework to isolate the input encoding component of contemporary quantum reservoir computing schemes. We find that across the majority of schemes the input encoding implements a nonlinear transformation on the input data. As nonlinearity is known to be a key computational resource in reservoir computing, this calls into question the necessity and function of further, post-input, processing. Our findings will impact the design of future quantum reservoirs, as well as the interpretation of results and fair comparison between proposed designs.

APA, Harvard, Vancouver, ISO, and other styles

10

Oliveira, Estevao Rada, and Fernando Juliani. "Reservoir Computing: uma Abordagem Conceitual." Revista de Ciências Exatas e Tecnologia 13, no. 13 (December 30, 2018): 09. http://dx.doi.org/10.17921/1890-1793.2018v13n13p09-12.

Full text

Abstract:

Reservoir computing é um paradigma de rede neural recorrente construída de forma aleatória, onde sua camada intermediária não necessita ser treinada. O presente artigo sintetiza os principais conceitos, métodos e pesquisas recentes realizadas sobre o paradigma de reservoir computing, objetivando servir como apoio teórico para outros artigos. Foi realizada uma revisão bibliográfica fundamentada em bases de conhecimento científico confiáveis enfatizando pesquisas compreendidas no período de 2007 a 2017 e direcionadas à implementação e otimização do paradigma em questão. Como resultado do trabalho, tem-se a apresentação de trabalhos recentes que contribuem de forma geral para o desenvolvimento de reservoir computing, e devido à atualidade do tema, é apresentada uma diversidade de tópicos abertos à pesquisa, podendo servir como norteamento para a comunidade científica. Palavras-chave: Aprendizado de Máquina. Inteligência Artificial. Redes Neurais Recorrentes.Abstract Reservoir computng is a randomly constructed recurrent neural network paradigm, where the hidden layer does not need to be trained. This article summarizes the main concepts, methods and recent researches about reservoir computing paradigm, aiming to offer a theoretical support for other articles. Were made a bibliographic review based on reliable scientific knowledge bases, emphasizing researches published between 2007 and 2017 and focused on implementation and optimization of aforementioned paradigm. As a result, there's a report of recent articles that contribute in general to the development of reservoir computing, and due to its topicality, a diversity of topics that are still open to research are given, that may possibly work as a guide for the research community. Keywords: Artificial Intelligence. Machine Learning. Recurrent Neural Network.

APA, Harvard, Vancouver, ISO, and other styles

11

Nikolić, Vladimir, Moriah Echlin, Boris Aguilar, and Ilya Shmulevich. "Computational capabilities of a multicellular reservoir computing system." PLOS ONE 18, no. 4 (April 6, 2023): e0282122. http://dx.doi.org/10.1371/journal.pone.0282122.

Full text

Abstract:

The capacity of cells to process information is currently used to design cell-based tools for ecological, industrial, and biomedical applications such as detecting dangerous chemicals or for bioremediation. In most applications, individual cells are used as the information processing unit. However, single cell engineering is limited by the necessary molecular complexity and the accompanying metabolic burden of synthetic circuits. To overcome these limitations, synthetic biologists have begun engineering multicellular systems that combine cells with designed subfunctions. To further advance information processing in synthetic multicellular systems, we introduce the application of reservoir computing. Reservoir computers (RCs) approximate a temporal signal processing task via a fixed-rule dynamic network (the reservoir) with a regression-based readout. Importantly, RCs eliminate the need of network rewiring, as different tasks can be approximated with the same reservoir. Previous work has already demonstrated the capacity of single cells, as well as populations of neurons, to act as reservoirs. In this work, we extend reservoir computing in multicellular populations with the widespread mechanism of diffusion-based cell-to-cell signaling. As a proof-of-concept, we simulated a reservoir made of a 3D community of cells communicating via diffusible molecules and used it to approximate a range of binary signal processing tasks, focusing on two benchmark functions—computing median and parity functions from binary input signals. We demonstrate that a diffusion-based multicellular reservoir is a feasible synthetic framework for performing complex temporal computing tasks that provides a computational advantage over single cell reservoirs. We also identified a number of biological properties that can affect the computational performance of these processing systems.

APA, Harvard, Vancouver, ISO, and other styles

12

Amer, Manar M., and Dahlia A. Al-Obaidi. "Methods Used to Estimate Reservoir Pressure Performance: A Review." Journal of Engineering 30, no. 06 (June 1, 2024): 83–107. http://dx.doi.org/10.31026/j.eng.2024.06.06.

Full text

Abstract:

Reservoir pressure plays a significant role in all reservoir and production engineering studies. It is crucial to characterize petroleum reservoirs: by detecting fluid movement, computing oil in place, and calculating the recovery factor. Knowledge of reservoir pressure is essential for predicting future production rates, optimizing well performance, or planning enhanced oil recovery strategies. However, applying the methods to investigate reservoir pressure performance is challenging because reservoirs are large, complex systems with irregular geometries in subsurface formations with numerous uncertainties and limited information about the reservoir's structure and behavior. Furthermore, many computational techniques, both numerical and analytical, have been utilized to examine reservoir pressure performance. This paper summarizes the concepts and applications of traditional and novel ways to investigate reservoir pressure changes over time. It provides a comprehensive review that assists the reader in recognizing and distinguishing between various techniques for obtaining an accurate description of reservoir pressure behavior during production, such as the reservoir simulation method, material balance equation approach, time-lapse seismic data, and modern artificial intelligence methods. Thus, the central concept of these procedures and a list of the authors' research are discussed.

APA, Harvard, Vancouver, ISO, and other styles

13

Ghosh, Sanjib, Kohei Nakajima, Tanjung Krisnanda, Keisuke Fujii, and Timothy C. H. Liew. "Quantum Neuromorphic Computing with Reservoir Computing Networks." Advanced Quantum Technologies 4, no. 9 (July 9, 2021): 2100053. http://dx.doi.org/10.1002/qute.202100053.

Full text

APA, Harvard, Vancouver, ISO, and other styles

14

Silva, Nuno Azevedo, Tiago D. Ferreira, and Ariel Guerreiro. "Reservoir computing with solitons." New Journal of Physics 23, no. 2 (February 1, 2021): 023013. http://dx.doi.org/10.1088/1367-2630/abda84.

Full text

APA, Harvard, Vancouver, ISO, and other styles

15

Lymburn, Thomas, Shannon D. Algar, Michael Small, and Thomas Jüngling. "Reservoir computing with swarms." Chaos: An Interdisciplinary Journal of Nonlinear Science 31, no. 3 (March 2021): 033121. http://dx.doi.org/10.1063/5.0039745.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

Galen-Prado, Fabio, J. Font-Rossello, and Josep L. Rossello. "Tropical Reservoir Computing Hardware." IEEE Transactions on Circuits and Systems II: Express Briefs 67, no. 11 (November 2020): 2712–16. http://dx.doi.org/10.1109/tcsii.2020.2966320.

Full text

APA, Harvard, Vancouver, ISO, and other styles

17

Obst, Oliver, Adrian Trinchi, Simon G. Hardin, Matthew Chadwick, Ivan Cole, Tim H. Muster, Nigel Hoschke, et al. "Nano-scale reservoir computing." Nano Communication Networks 4, no. 4 (December 2013): 189–96. http://dx.doi.org/10.1016/j.nancom.2013.08.005.

Full text

APA, Harvard, Vancouver, ISO, and other styles

18

Duport, François, Bendix Schneider, Anteo Smerieri, Marc Haelterman, and Serge Massar. "All-optical reservoir computing." Optics Express 20, no. 20 (September 20, 2012): 22783. http://dx.doi.org/10.1364/oe.20.022783.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Ortín, Silvia, and Luis Pesquera. "Reservoir Computing with an Ensemble of Time-Delay Reservoirs." Cognitive Computation 9, no. 3 (April 5, 2017): 327–36. http://dx.doi.org/10.1007/s12559-017-9463-7.

Full text

APA, Harvard, Vancouver, ISO, and other styles

20

Su, Chang, Gang Zhao, Yee-Chung Jin, and Wanju Yuan. "Semi-Analytical Modeling of Geological Features Based Heterogeneous Reservoirs Using the Boundary Element Method." Minerals 12, no. 6 (May 24, 2022): 663. http://dx.doi.org/10.3390/min12060663.

Full text

Abstract:

The objective of this work is to innovatively apply the boundary element method (BEM) as a general modeling strategy to deal with complicated reservoir modeling problems, especially those related to reservoir heterogeneity and fracture systems, which are common challenges encountered in the practice of reservoir engineering. The transient flow behaviors of reservoirs containing multi-scale heterogeneities enclosed by arbitrarily shaped boundaries are modeled by applying BEM. We demonstrate that a BEM-based simulation strategy is capable of modeling complex heterogeneous reservoirs with robust solutions. The technology is beneficial in making the best use of geological modeling information. The governing differential operator of fluid flow within any locally homogeneous domain is solved along its boundary. The discretization of a reservoir system is only made on the corresponding boundaries, which is advantageous in closely conforming to the reservoir’s geological description and in facilitating the numerical simulation and computational efforts because no gridding within the flow domain is needed. Theoretical solutions, in terms of pressure and flow rate responses, are validated and exemplified for various reservoir–well systems, including naturally fractured reservoirs with either non-crossing fractures or crossing fractures; fully compartmentalized reservoirs; and multi-stage, fractured, horizontal wells with locally stimulated reservoir volumes (SRVs) around each stage of the fracture, etc. A challenging case study for a complicated fracture network system is examined. This work demonstrates the significance of adapting the BEM strategy for reservoir simulation due to its flexibility in modeling reservoir heterogeneity, analytical solution accuracy, and high computing efficiency, in reducing the technical gap between reservoir engineering practice and simulation capacity.

APA, Harvard, Vancouver, ISO, and other styles

21

Namiki, Wataru, Daiki Nishioka, Takashi Tsuchiya, and Kazuya Terabe. "Fast physical reservoir computing, achieved with nonlinear interfered spin waves." Neuromorphic Computing and Engineering 4, no. 2 (June 1, 2024): 024015. http://dx.doi.org/10.1088/2634-4386/ad561a.

Full text

Abstract:

Abstract Reservoir computing is a promising approach to implementing high-performance artificial intelligence that can process input data at lower computational costs than conventional artificial neural networks. Although reservoir computing enables real-time processing of input time-series data on artificial intelligence mounted on terminal devices, few physical devices are capable of high-speed operation for real-time processing. In this study, we introduce spin wave interference with a stepped input method to reduce the operating time of the physical reservoir, and second-order nonlinear equation task and second-order nonlinear autoregressive mean averaging, which are well-known benchmark tasks, were carried out to evaluate the operating speed and prediction accuracy of said physical reservoir. The demonstrated reservoir device operates at the shortest operating time of 13 ms/5000-time steps, compared to other compact reservoir devices, even though its performance is higher than or comparable to such physical reservoirs. This study is a stepping stone toward realizing an artificial intelligence device capable of real-time processing on terminal devices.

APA, Harvard, Vancouver, ISO, and other styles

22

Jaurigue, Lina, Elizabeth Robertson, Janik Wolters, and Kathy Lüdge. "Reservoir Computing with Delayed Input for Fast and Easy Optimisation." Entropy 23, no. 12 (November 23, 2021): 1560. http://dx.doi.org/10.3390/e23121560.

Full text

Abstract:

Reservoir computing is a machine learning method that solves tasks using the response of a dynamical system to a certain input. As the training scheme only involves optimising the weights of the responses of the dynamical system, this method is particularly suited for hardware implementation. Furthermore, the inherent memory of dynamical systems which are suitable for use as reservoirs mean that this method has the potential to perform well on time series prediction tasks, as well as other tasks with time dependence. However, reservoir computing still requires extensive task-dependent parameter optimisation in order to achieve good performance. We demonstrate that by including a time-delayed version of the input for various time series prediction tasks, good performance can be achieved with an unoptimised reservoir. Furthermore, we show that by including the appropriate time-delayed input, one unaltered reservoir can perform well on six different time series prediction tasks at a very low computational expense. Our approach is of particular relevance to hardware implemented reservoirs, as one does not necessarily have access to pertinent optimisation parameters in physical systems but the inclusion of an additional input is generally possible.

APA, Harvard, Vancouver, ISO, and other styles

23

Sun, Xiaochuan, Jiahui Gao, Yu Wang, Yingqi Li, and Xin Feng. "Towards Fault Tolerance of Reservoir Computing in Time Series Prediction." Information 14, no. 5 (April 30, 2023): 266. http://dx.doi.org/10.3390/info14050266.

Full text

Abstract:

During the deployment of practical applications, reservoir computing (RC) is highly susceptible to radiation effects, temperature changes, and other factors. Normal reservoirs are difficult to vouch for. To solve this problem, this paper proposed a random adaptive fault tolerance mechanism for an echo state network, i.e., RAFT-ESN, to handle the crash or Byzantine faults of reservoir neurons. In our consideration, the faulty neurons were automatically detected and located based on the abnormalities of reservoir state output. The synapses connected to them were adaptively disconnected and withdrawn from the current computational task. On the widely used time series with different sources and features, the experimental results show that our proposal can achieve an effective performance recovery in the case of reservoir neuron faults, including prediction accuracy and short-term memory capacity (MC). Additionally, its utility was validated by statistical distributions.

APA, Harvard, Vancouver, ISO, and other styles

24

Toutounji, Hazem, Johannes Schumacher, and Gordon Pipa. "Homeostatic Plasticity for Single Node Delay-Coupled Reservoir Computing." Neural Computation 27, no. 6 (June 2015): 1159–85. http://dx.doi.org/10.1162/neco_a_00737.

Full text

Abstract:

Supplementing a differential equation with delays results in an infinite-dimensional dynamical system. This property provides the basis for a reservoir computing architecture, where the recurrent neural network is replaced by a single nonlinear node, delay-coupled to itself. Instead of the spatial topology of a network, subunits in the delay-coupled reservoir are multiplexed in time along one delay span of the system. The computational power of the reservoir is contingent on this temporal multiplexing. Here, we learn optimal temporal multiplexing by means of a biologically inspired homeostatic plasticity mechanism. Plasticity acts locally and changes the distances between the subunits along the delay, depending on how responsive these subunits are to the input. After analytically deriving the learning mechanism, we illustrate its role in improving the reservoir’s computational power. To this end, we investigate, first, the increase of the reservoir’s memory capacity. Second, we predict a NARMA-10 time series, showing that plasticity reduces the normalized root-mean-square error by more than 20%. Third, we discuss plasticity’s influence on the reservoir’s input-information capacity, the coupling strength between subunits, and the distribution of the readout coefficients.

APA, Harvard, Vancouver, ISO, and other styles

25

NAKAYAMA, Joma, Kazutaka KANNO, Masatoshi BUNSEN, and Atsushi UCHIDA. "Reservoir Computing: Novel Optical Computing Using Laser Dynamics." Review of Laser Engineering 43, no. 6 (2015): 365. http://dx.doi.org/10.2184/lsj.43.6_365.

Full text

APA, Harvard, Vancouver, ISO, and other styles

26

Salehi, M. R., E. Abiri, and L. Dehyadegari. "Nanophotonic Reservoir Computing for Noisy Time Series Classification." International Journal of Computer and Electrical Engineering 6, no. 3 (2014): 240–43. http://dx.doi.org/10.7763/ijcee.2014.v6.830.

Full text

APA, Harvard, Vancouver, ISO, and other styles

27

Harkhoe, Krishan, and Guy Van der Sande. "Task-Independent Computational Abilities of Semiconductor Lasers with Delayed Optical Feedback for Reservoir Computing." Photonics 6, no. 4 (December 2, 2019): 124. http://dx.doi.org/10.3390/photonics6040124.

Full text

Abstract:

Reservoir computing has rekindled neuromorphic computing in photonics. One of the simplest technological implementations of reservoir computing consists of a semiconductor laser with delayed optical feedback. In this delay-based scheme, virtual nodes are distributed in time with a certain node distance and form a time-multiplexed network. The information processing performance of a semiconductor laser-based reservoir computing (RC) system is usually analysed by way of testing the laser-based reservoir computer on specific benchmark tasks. In this work, we will illustrate the optimal performance of the system on a chaotic time-series prediction benchmark. However, the goal is to analyse the reservoir’s performance in a task-independent way. This is done by calculating the computational capacity, a measure for the total number of independent calculations that the system can handle. We focus on the dependence of the computational capacity on the specifics of the masking procedure. We find that the computational capacity depends strongly on the virtual node distance with an optimal node spacing of 30 ps. In addition, we show that the computational capacity can be further increased by allowing for a well chosen mismatch between delay and input data sample time.

APA, Harvard, Vancouver, ISO, and other styles

28

SalamAbdAlRasool, Ahmed, and Sulaiman Murtadha Abbas. "Movement Prediction using Reservoir Computing." International Journal of Computer Applications 69, no. 8 (May 17, 2013): 17–33. http://dx.doi.org/10.5120/11862-7646.

Full text

APA, Harvard, Vancouver, ISO, and other styles

29

Nakajima, Mitsumasa, Takuma Tsurugaya, Kenji Tanaka, and Toshikazu Hashimoto. "Photonic Implementation of Reservoir Computing." NTT Technical Review 20, no. 8 (August 2022): 58–63. http://dx.doi.org/10.53829/ntr202208fa8.

Full text

APA, Harvard, Vancouver, ISO, and other styles

30

Liu, Xingyi, and Keshab K. Parhi. "Reservoir Computing Using DNA Oscillators." ACS Synthetic Biology 11, no. 2 (January 26, 2022): 780–87. http://dx.doi.org/10.1021/acssynbio.1c00483.

Full text

APA, Harvard, Vancouver, ISO, and other styles

31

S Pathak, Shantanu, and D. Rajeswara Rao. "Reservoir Computing for Healthcare Analytics." International Journal of Engineering & Technology 7, no. 2.32 (May 31, 2018): 240. http://dx.doi.org/10.14419/ijet.v7i2.32.15576.

Full text

Abstract:

In this data age tools for sophisticated generation and handling of data are at epitome of usage. Data varying in both space and time poses a breed of challenges. Challenges they possess for forecasting can be well handled by Reservoir computing based neural networks. Challenges like class imbalance, missing values, locality effect are discussed here. Additionally, popular statistical techniques for forecasting such data are discussed. Results show how Reservoir Computing based technique outper-forms traditional neural networks.

APA, Harvard, Vancouver, ISO, and other styles

32

Andrecut, M. "Reservoir computing on the hypersphere." International Journal of Modern Physics C 28, no. 07 (July 2017): 1750095. http://dx.doi.org/10.1142/s0129183117500954.

Full text

Abstract:

Reservoir Computing (RC) refers to a Recurrent Neural Network (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 classifier (the hidden-output readout layer). Here, we focus on the sequence learning problem, and we explore a different approach to RC. More specifically, we remove the nonlinear neural activation function, and we consider an orthogonal reservoir acting on normalized states on the unit hypersphere. Surprisingly, our numerical results show that the system’s memory capacity exceeds the dimensionality of the reservoir, which is the upper bound for the typical RC approach based on Echo State Networks (ESNs). We also show how the proposed system can be applied to symmetric cryptography problems, and we include a numerical implementation.

APA, Harvard, Vancouver, ISO, and other styles

33

Bienstman, Peter, Kristof Vandoorne, Thomas Van Vaerenbergh, Martin Fiers, Bendix Schneider, David Verstraeten, Benjamin Schrauwen, and Joni Dambre. "Reservoir computing on nanophotonic chips." IEICE Proceeding Series 1 (March 17, 2014): 506–8. http://dx.doi.org/10.15248/proc.1.506.

Full text

APA, Harvard, Vancouver, ISO, and other styles

34

Seoane, Luís F. "Evolutionary aspects of reservoir computing." Philosophical Transactions of the Royal Society B: Biological Sciences 374, no. 1774 (April 22, 2019): 20180377. http://dx.doi.org/10.1098/rstb.2018.0377.

Full text

Abstract:

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 reservoir with highly nonlinear dynamics that does not require a fine tuning of its parts. These dynamics project input signals into high-dimensional spaces, where training linear readouts to extract input features is vastly simplified. Thus, inexpensive learning provides very powerful tools for decision-making, controlling dynamical systems, classification, etc. RC also facilitates solving multiple tasks in parallel, resulting in a high throughput. Existing literature focuses on applications in artificial intelligence and neuroscience. We review this literature from an evolutionary perspective. RC’s versatility makes it a great candidate to solve outstanding problems in biology, which raises relevant questions. Is RC as abundant in nature as its advantages should imply? Has it evolved? Once evolved, can it be easily sustained? Under what circumstances? (In other words, is RC an evolutionarily stable computing paradigm?) To tackle these issues, we introduce a conceptual morphospace that would map computational selective pressures that could select for or against RC and other computing paradigms. This guides a speculative discussion about the questions above and allows us to propose a solid research line that brings together computation and evolution with RC as test model of the proposed hypotheses. This article is part of the theme issue ‘Liquid brains, solid brains: How distributed cognitive architectures process information’.

APA, Harvard, Vancouver, ISO, and other styles

35

Rohm, Andre, Lina Jaurigue, and Kathy Ludge. "Reservoir Computing Using Laser Networks." IEEE Journal of Selected Topics in Quantum Electronics 26, no. 1 (January 2020): 1–8. http://dx.doi.org/10.1109/jstqe.2019.2927578.

Full text

APA, Harvard, Vancouver, ISO, and other styles

36

Reinhart, René Felix. "Reservoir Computing with Output Feedback." KI - Künstliche Intelligenz 26, no. 4 (April 6, 2012): 415–16. http://dx.doi.org/10.1007/s13218-012-0187-2.

Full text

APA, Harvard, Vancouver, ISO, and other styles

37

Marinella, Matthew J., and Sapan Agarwal. "Efficient reservoir computing with memristors." Nature Electronics 2, no. 10 (October 2019): 437–38. http://dx.doi.org/10.1038/s41928-019-0318-y.

Full text

APA, Harvard, Vancouver, ISO, and other styles

38

Damicelli, Fabrizio, Claus C. Hilgetag, and Alexandros Goulas. "Brain connectivity meets reservoir computing." PLOS Computational Biology 18, no. 11 (November 16, 2022): e1010639. http://dx.doi.org/10.1371/journal.pcbi.1010639.

Full text

Abstract:

The connectivity of Artificial Neural Networks (ANNs) is different from the one observed in Biological Neural Networks (BNNs). Can the wiring of actual brains help improve ANNs architectures? Can we learn from ANNs about what network features support computation in the brain when solving a task? At a meso/macro-scale level of the connectivity, ANNs’ architectures are carefully engineered and such those design decisions have crucial importance in many recent performance improvements. On the other hand, BNNs exhibit complex emergent connectivity patterns at all scales. At the individual level, BNNs connectivity results from brain development and plasticity processes, while at the species level, adaptive reconfigurations during evolution also play a major role shaping connectivity. Ubiquitous features of brain connectivity have been identified in recent years, but their role in the brain’s ability to perform concrete computations remains poorly understood. Computational neuroscience studies reveal the influence of specific brain connectivity features only on abstract dynamical properties, although the implications of real brain networks topologies on machine learning or cognitive tasks have been barely explored. Here we present a cross-species study with a hybrid approach integrating real brain connectomes and Bio-Echo State Networks, which we use to solve concrete memory tasks, allowing us to probe the potential computational implications of real brain connectivity patterns on task solving. We find results consistent across species and tasks, showing that biologically inspired networks perform as well as classical echo state networks, provided a minimum level of randomness and diversity of connections is allowed. We also present a framework, bio2art, to map and scale up real connectomes that can be integrated into recurrent ANNs. This approach also allows us to show the crucial importance of the diversity of interareal connectivity patterns, stressing the importance of stochastic processes determining neural networks connectivity in general.

APA, Harvard, Vancouver, ISO, and other styles

39

Midya, Rivu, Zhongrui Wang, Shiva Asapu, Xumeng Zhang, Mingyi Rao, Wenhao Song, Ye Zhuo, Navnidhi Upadhyay, Qiangfei Xia, and J. Joshua Yang. "Reservoir Computing Using Diffusive Memristors." Advanced Intelligent Systems 1, no. 7 (September 25, 2019): 1900084. http://dx.doi.org/10.1002/aisy.201900084.

Full text

APA, Harvard, Vancouver, ISO, and other styles

40

Tkachuk, Andrii G., Mariia S. Hrynevych, Tetiana A. Vakaliuk, Oksana A. Chernysh, and Mykhailo G. Medvediev. "Edge computing in environmental science: automated intelligent robotic platform for water quality assessment." Journal of Edge Computing 2, no. 2 (November 19, 2023): 163–74. http://dx.doi.org/10.55056/jec.633.

Full text

Abstract:

This paper introduces a novel intelligent robotic platform designed to expedite and enhance the process of water quality assessment and bottom relief analysis in reservoirs. The platform, equipped with an array of sensors and actuators, is capable of conducting comprehensive studies over larger areas of the reservoir, thereby overcoming the limitations of traditional water analysis methods. The platform’s advanced design includes a control board, servo motors, a brushless motor, a radio module, a GPS module, and a motor speed controller, all housed within a robust casing. The paper presents a functional diagram of the platform and discusses the results of a system study conducted on a reservoir. The study aimed to verify the system’s operation, evaluate the effectiveness of the research conducted, and calibrate water quality sensors. The platform utilizes an ultrasonic sensor for depth measurement and sensors for water acidity and temperature. The results of the monitoring system experiments led to the creation of a detailed map of the reservoir’s bottom area and provided valuable insights into water quality.

APA, Harvard, Vancouver, ISO, and other styles

41

Aoun, Muhammad, Shafiq Ur Rehman, and Rawal Javed. "Enhancing reservoir computing for secure digital image encryption using finance model forecasting." Natural and Applied Sciences International Journal (NASIJ) 4, no. 2 (December 13, 2023): 63–77. http://dx.doi.org/10.47264/idea.nasij/4.2.4.

Full text

Abstract:

New research is changing the face of financial forecasting by combining reservoir computing with digital image encryption at a time when data security is of the utmost importance. This groundbreaking study combines digital image encryption with reservoir computing to suggest a novel method for financial forecasting. This creative method uses a reservoir network to encrypt digital photos securely, increasing their resistance to attacks and demonstrating the power of reservoir computing, a well-known machine learning concept. This approach significantly improves financial time series data forecasting accuracy and reliability using hyper-clusteratic models. When reservoir computing and hyper-chaotic models are tightly integrated, outcome is improved financial decision-making. Empirical tests have validated the technology's effectiveness and efficiency, showcasing its potential practical applications in financial forecasting and image encryption. The study examines numerical simulations in a dynamic reservoir framework that demonstrate encryption and decryption powers of reservoir computing, demonstrating its ability to comprehend input signals and generate answers that are desired. Critical phases include assessing the approach's effectiveness using metrics for encryption quality, attack resilience, and computing efficiency. Preparing picture representations for processing is also crucial. It is necessary to train the readout layer to translate reservoir states to encrypted picture pixels differently.

APA, Harvard, Vancouver, ISO, and other styles

42

Pyle, Ryan, and Robert Rosenbaum. "A Reservoir Computing Model of Reward-Modulated Motor Learning and Automaticity." Neural Computation 31, no. 7 (July 2019): 1430–61. http://dx.doi.org/10.1162/neco_a_01198.

Full text

Abstract:

Reservoir computing is a biologically inspired class of learning algorithms in which the intrinsic dynamics of a recurrent neural network are mined to produce target time series. Most existing reservoir computing algorithms rely on fully supervised learning rules, which require access to an exact copy of the target response, greatly reducing the utility of the system. Reinforcement learning rules have been developed for reservoir computing, but we find that they fail to converge on complex motor tasks. Current theories of biological motor learning pose that early learning is controlled by dopamine-modulated plasticity in the basal ganglia that trains parallel cortical pathways through unsupervised plasticity as a motor task becomes well learned. We developed a novel learning algorithm for reservoir computing that models the interaction between reinforcement and unsupervised learning observed in experiments. This novel learning algorithm converges on simulated motor tasks on which previous reservoir computing algorithms fail and reproduces experimental findings that relate Parkinson's disease and its treatments to motor learning. Hence, incorporating biological theories of motor learning improves the effectiveness and biological relevance of reservoir computing models.

APA, Harvard, Vancouver, ISO, and other styles

43

Katumba, Andrew, Matthias Freiberger, Floris Laporte, Alessio Lugnan, Stijn Sackesyn, Chonghuai Ma, Joni Dambre, and Peter Bienstman. "Neuromorphic Computing Based on Silicon Photonics and Reservoir Computing." IEEE Journal of Selected Topics in Quantum Electronics 24, no. 6 (November 2018): 1–10. http://dx.doi.org/10.1109/jstqe.2018.2821843.

Full text

APA, Harvard, Vancouver, ISO, and other styles

44

Hasegawa, Hiroshi, Kazutaka Kanno, and Atsushi Uchida. "Parallel and deep reservoir computing using semiconductor lasers with optical feedback." Nanophotonics, October 17, 2022. http://dx.doi.org/10.1515/nanoph-2022-0440.

Full text

Abstract:

Abstract Photonic reservoir computing has been intensively investigated to solve machine learning tasks effectively. A simple learning procedure of output weights is used for reservoir computing. However, the lack of training of input-node and inter-node connection weights limits the performance of reservoir computing. The use of multiple reservoirs can be a solution to overcome this limitation of reservoir computing. In this study, we investigate parallel and deep configurations of delay-based all-optical reservoir computing using semiconductor lasers with optical feedback by combining multiple reservoirs to improve the performance of reservoir computing. Furthermore, we propose a hybrid configuration to maximize the benefits of parallel and deep reservoirs. We perform the chaotic time-series prediction task, nonlinear channel equalization task, and memory capacity measurement. Then, we compare the performance of single, parallel, deep, and hybrid reservoir configurations. We find that deep reservoirs are suitable for a chaotic time-series prediction task, whereas parallel reservoirs are suitable for a nonlinear channel equalization task. Hybrid reservoirs outperform other configurations for all three tasks. We further optimize the number of reservoirs for each reservoir configuration. Multiple reservoirs show great potential for the improvement of reservoir computing, which in turn can be applied for high-performance edge computing.

APA, Harvard, Vancouver, ISO, and other styles

45

Edwards, Alexander J., Dhritiman Bhattacharya, Peng Zhou, Nathan R. McDonald, Walid Al Misba, Lisa Loomis, Felipe García-Sánchez, et al. "Passive frustrated nanomagnet reservoir computing." Communications Physics 6, no. 1 (August 17, 2023). http://dx.doi.org/10.1038/s42005-023-01324-8.

Full text

Abstract:

AbstractReservoir computing (RC) has received recent interest because reservoir weights do not need to be trained, enabling extremely low-resource consumption implementations, which could have a transformative impact on edge computing and in-situ learning where resources are severely constrained. Ideally, a natural hardware reservoir should be passive, minimal, expressive, and feasible; to date, proposed hardware reservoirs have had difficulty meeting all of these criteria. We, therefore, propose a reservoir that meets all of these criteria by leveraging the passive interactions of dipole-coupled, frustrated nanomagnets. The frustration significantly increases the number of stable reservoir states, enriching reservoir dynamics, and as such these frustrated nanomagnets fulfill all of the criteria for a natural hardware reservoir. We likewise propose a complete frustrated nanomagnet reservoir computing (NMRC) system with low-power complementary metal-oxide semiconductor (CMOS) circuitry to interface with the reservoir, and initial experimental results demonstrate the reservoir’s feasibility. The reservoir is verified with micromagnetic simulations on three separate tasks demonstrating expressivity. The proposed system is compared with a CMOS echo state network (ESN), demonstrating an overall resource decrease by a factor of over 10,000,000, demonstrating that because NMRC is naturally passive and minimal it has the potential to be extremely resource efficient.

APA, Harvard, Vancouver, ISO, and other styles

46

Abdi, Gisya, Tomasz Mazur, and Konrad Szaciłowski. "Organised view on reservoir computing: a perspective on theory and technology development." Japanese Journal of Applied Physics, April 1, 2024. http://dx.doi.org/10.35848/1347-4065/ad394f.

Full text

Abstract:

Abstract Reservoir computing is an unconventional computing paradigm that uses system complexity and dynamics as computational medium. Currently it is the leading computational paradigm in the fields of unconventional in materia computing. This review briefly outlines the theory behind the term ‘reservoir computing’, presents the basis for evaluation of reservoirs and presents a cultural reference of reservoir computing in haiku. The summary highlights recent advances in physical reservoir computing and points out the importance of the drive, usually neglected in physical implementations of reservoir computing. However, drive signals may further simplify the training of reservoirs’ readout layer training, thus contributing to improved performance of reservoir computer performance.

APA, Harvard, Vancouver, ISO, and other styles

47

Nishioka, Daiki, Takashi Tsuchiya, Masataka Imura, Yasuo Koide, Tohru Higuchi, and Kazuya Terabe. "A high-performance deep reservoir computer experimentally demonstrated with ion-gating reservoirs." Communications Engineering 3, no. 1 (June 19, 2024). http://dx.doi.org/10.1038/s44172-024-00227-y.

Full text

Abstract:

AbstractWhile physical reservoir computing is a promising way to achieve low power consumption neuromorphic computing, its computational performance is still insufficient at a practical level. One promising approach to improving its performance is deep reservoir computing, in which the component reservoirs are multi-layered. However, all of the deep-reservoir schemes reported so far have been effective only for simulation reservoirs and limited physical reservoirs, and there have been no reports of nanodevice implementations. Here, as an ionics-based neuromorphic nanodevice implementation of deep-reservoir computing, we report a demonstration of deep physical reservoir computing with maximum of four layers using an ion gating reservoir, which is a small and high-performance physical reservoir. While the previously reported deep-reservoir scheme did not improve the performance of the ion gating reservoir, our deep-ion gating reservoir achieved a normalized mean squared error of 9.08 × 10−3 on a second-order nonlinear autoregressive moving average task, which is the best performance of any physical reservoir so far reported in this task. More importantly, the device outperformed full simulation reservoir computing. The dramatic performance improvement of the ion gating reservoir with our deep-reservoir computing architecture paves the way for high-performance, large-scale, physical neural network devices.

APA, Harvard, Vancouver, ISO, and other styles

48

Allenspach, R., A. Bischof, and R. Heller. "Antidot lattices for magnetic reservoir computing." Applied Physics Letters 125, no. 22 (November 25, 2024). http://dx.doi.org/10.1063/5.0240085.

Full text

Abstract:

Reservoir computing can be implemented in a variety of systems beyond standard CMOS technology. Here, we describe a scheme that relies on a magnetic reservoir consisting of an antidot array, motivated by earlier experiments on ring arrays. We show that antidot lattices can be used as reservoirs much in the same way as ring arrays. We describe geometries in which smaller magnetic fields are needed to induce emergent magnetic patterns in the reservoir, a prerequisite for its use in reservoir computing. High-resolution magnetic imaging of these patterns shows entirely different domains and domain walls, despite the fact that the macroscopic magnetic signal behaves very similarly in both types of reservoirs.

APA, Harvard, Vancouver, ISO, and other styles

49

Liang, Xiangpeng, Yanan Zhong, Jianshi Tang, Zhengwu Liu, Peng Yao, Keyang Sun, Qingtian Zhang, et al. "Rotating neurons for all-analog implementation of cyclic reservoir computing." Nature Communications 13, no. 1 (March 23, 2022). http://dx.doi.org/10.1038/s41467-022-29260-1.

Full text

Abstract:

AbstractHardware implementation in resource-efficient reservoir computing is of great interest for neuromorphic engineering. Recently, various devices have been explored to implement hardware-based reservoirs. However, most studies were mainly focused on the reservoir layer, whereas an end-to-end reservoir architecture has yet to be developed. Here, we propose a versatile method for implementing cyclic reservoirs using rotating elements integrated with signal-driven dynamic neurons, whose equivalence to standard cyclic reservoir algorithm is mathematically proven. Simulations show that the rotating neuron reservoir achieves record-low errors in a nonlinear system approximation benchmark. Furthermore, a hardware prototype was developed for near-sensor computing, chaotic time-series prediction and handwriting classification. By integrating a memristor array as a fully-connected output layer, the all-analog reservoir computing system achieves 94.0% accuracy, while simulation shows >1000× lower system-level power than prior works. Therefore, our work demonstrates an elegant rotation-based architecture that explores hardware physics as computational resources for high-performance reservoir computing.

APA, Harvard, Vancouver, ISO, and other styles

50

Shreya, S., A. S. Jenkins, Y. Rezaeiyan, R. Li, T. Böhnert, L. Benetti, R. Ferreira, F. Moradi, and H. Farkhani. "Granular vortex spin-torque nano oscillator for reservoir computing." Scientific Reports 13, no. 1 (October 4, 2023). http://dx.doi.org/10.1038/s41598-023-43923-z.

Full text

Abstract:

AbstractIn this paper, we investigate the granularity in the free layer of the magnetic tunnel junctions (MTJ) and its potential to function as a reservoir for reservoir computing where grains act as oscillatory neurons while the device is in the vortex state. The input of the reservoir is applied in the form of a magnetic field which can pin the vortex core into different grains of the device in the magnetic vortex state. The oscillation frequency and MTJ resistance vary across different grains in a non-linear fashion making them great candidates to be served as the reservoir's outputs for classification objectives. Hence, we propose an experimentally validated area-efficient single granular vortex spin-torque nano oscillator (GV-STNO) device in which pinning sites work as random reservoirs that can emulate neuronal functions. We harness the nonlinear oscillation frequency and resistance exhibited by the vortex core granular pinning of the GV-STNO reservoir computing system to demonstrate waveform classification.

APA, Harvard, Vancouver, ISO, and other styles

We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!