Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication
The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
We present a method for learning nonlinear systems, echo state networks (ESNs). ESNs employ artificial recurrent neural networks in a way that has recently been proposed independently as a learning mechanism in biological brains. The learning method is computationally efficient and easy to use. On a benchmark task of predicting a chaotic time series, accuracy is improved by a factor of 2400 over previous techniques. The potential for engineering applications is illustrated by equalizing a communication channel, where the signal error rate is improved by two orders of magnitude.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Although work in artificial intelligence and machine-learning research has shown that similar or even more complex outcomes can be achieved with a variety of techniques, including deep neural networks with trained weights (Gibney, 2015), reservoir networks with a trained output mapping (Maass et al., 2002;Jaeger & Haas, 2004), networks that are evolved using a genetic algorithm (Iizuka & Di Paolo,”
From A potential mechanism for Gibsonian resonance: behavioral entrainment emerges from local homeostasis in an unsupervised reservoir network (2024) · cites this paper as Jaeger & Haas, 2004
In the citing paper
“Therefore, a sequence production solely by a recurrent neural network can be unstable against small fluctuations in activities and unwanted noises (Jaeger and Haas, 2004).”
From The Cerebro-Cerebellum as a Locus of Forward Model: A Review (2020) · cites this paper as Jaeger and Haas, 2004
Citations
Cites
Backpropagation through time: what it does and how to do it
Werbos, P. J. (1990) · Proceedings of the IEEE · doi:10.1109/5.58337 · Cited by 4,879
A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
Williams, R. J., & Zipser, D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.2.270 · Cited by 4,369
Oscillation and Chaos in Physiological Control Systems
Mackey, M. C., & Glass, L. (1977) · Science · doi:10.1126/science.267326 · Cited by 4,135
Maass, W., Natschläger, T., & Markram, H. (2002) · Neural Computation · doi:10.1162/089976602760407955 · Cited by 4,025
Real-time prediction of hand trajectory by ensembles of cortical neurons in primates
Wessberg, J., Stambaugh, C. R., Kralik, J. D., Beck, P. D., Laubach, M., Chapin, J. K., Kim, J., Biggs, S. J., Srinivasan, M. A., & Nicolelis, M. A. L. (2000) · Nature · doi:10.1038/35042582 · Cited by 1,487
'Neural-gas' network for vector quantization and its application to time-series prediction
Martinetz, T. M., Berkovich, S. G., & Schulten, K. J. (1993) · IEEE Transactions on Neural Networks · doi:10.1109/72.238311 · Cited by 1,431
Approximation of dynamical systems by continuous time recurrent neural networks
Funahashi, K.-I., & Nakamura, Y. (1993) · Neural Networks · doi:10.1016/s0893-6080(05)80125-x · Cited by 980
A new evolutionary system for evolving artificial neural networks
Yao, X., & Liu, Y. (1997) · IEEE Transactions on Neural Networks · doi:10.1109/72.572107 · Cited by 874
Applying LSTM to Time Series Predictable through Time-Window Approaches
Gers, F. A., Eck, D., & Schmidhuber, J. (2001) · Lecture Notes in Computer Science · doi:10.1007/3-540-44668-0_93 · Cited by 334
Computational neuroscience: a comprehensive approach
(2004) · Choice Reviews Online · doi:10.5860/choice.41-5284 · Cited by 279
Research works printed but not linked: 10
- K. Doya, in The Handbook of Brain Theory and Neural Networks, M. A. Arbib, Ed. (MIT Press, Cambridge, MA, 1995), pp. 796–800.
- J. Vesanto in Proc. WSOM'97 (1997); www.cis.hut.fi/projects/monitor/publications/papers/wsom97.ps.
- L. Chudy, I. Farkas, Neural Network World8, 481 (1998).
- H. Bersini M. Birattari G. Bontempi in Proc. IEEE World Congr. on Computational Intelligence (IJCNN'98) (1997) pp. 2102–2106; ftp://iridia.ulb.ac.be/pub/lazy/papers/IridiaTr1997-13_2.ps.gz.
- V. J. Mathews, J. Lee, in Advanced Signal Processing: Algorithms, Architectures, and Implementations V (Proc. SPIE Vol. 2296), (SPIE, San Diego, CA, 1994), pp. 317–327.
- J. Hertzberg H. Jaeger F. Schönherr in Proc. 15th Europ. Conf. on Art. Int. (ECAI 02) F. van Harmelen Ed. (IOS Press Amsterdam 2002) pp. 708–712; www.ais.fhg.de/∼schoenhe/papers/ECAI02.pdf.
- H. Jaeger, in Advances in Neural Information Processing Systems 15, S. Becker, S. Thrun, K. Obermayer, Eds. (MIT Press, Cambridge, MA, 2003) pp. 593–600.
- G. E. Hinton, in Parallel Models of Associative Memory, G. E. Hinton, J. A. Anderson, Eds. (Erlbaum, Hillsdale, NJ, 1981), pp. 161–187.
- M. Kawato, in The Handbook of Brain Theory and Neural Networks, M. Arbib, Ed. (MIT Press, Cambridge, MA, 1995), pp. 172–178.
- G. B. Stanley, Neurocomputing38–40, 1703 (2001).
Cited by
Items 901–1,000 of 1,009
Forecasting Hamiltonian dynamics without canonical coordinates
Choudhary, A., Lindner, J. F., Holliday, E. G., Miller, S. T., Sinha, S., & Ditto, W. L. (2021) · Nonlinear Dynamics · doi:10.1007/s11071-020-06185-2 · Cited by 31
Lai, Y.-C. (2021) · Chaos An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/5.0062042 · Cited by 33
“In particular, a class of recurrent neural networks [133–136], the so-called reservoir computing machines, have attracted considerable attention since 2017 as a powerful paradigm for model-free, fully data driven prediction of nonlinear and chaotic dynamical systems [137–152].”
BackgroundReservoir Computing Based on Two Parallel Reservoirs Under Identical Electrical Message Injection
Yue, D., Wu, Z.-M., Hou, Y., Hu, C., Jiang, Z., & Xia, G.-Q. (2021) · IEEE photonics journal · doi:10.1109/jphot.2020.3048702 · Cited by 31
“Reservoir computing (RC), originally introduced as an echo state network and a liquid state machine [1], [2], is a novel information processing technique emerged in the field of machine learning and has evolved into a popular algorithm for processing complex tasks in recent years”
BackgroundA Comparison of Data‐Driven Approaches to Build Low‐Dimensional Ocean Models
Agarwal, N., Kondrashov, D., Dueben, P. D., Ryzhov, E. A., & Berloff, P. (2021) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2021ms002537 · Cited by 38
“LSTMs (Hochreiter & Schmidhuber, 1997) and reservoir computing (Jaeger & Haas, 2004; Nadiga, 2021; Pathak et al., 2018) are specific forms of Recurrent NNs that can progress learned information from one timestep to the next when applied in an iterative way.”
BackgroundRC-Struct: A Structure-Based Neural Network Approach for MIMO-OFDM Detection
Xu, J., Zhou, Z., Li, L., Zheng, L., & Liu, L. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3155945 · Cited by 38
Liao, Z., Wang, Z., Yamahara, H., & Tabata, H. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.09.074 · Cited by 33
Catch-22s of reservoir computing
Zhang, Y., & Cornelius, S. P. (2023) · Physical Review Research · doi:10.1103/physrevresearch.5.033213 · Cited by 41
“The basin prediction problem poses distinct challenges from the problem of forecasting chaotic systems, a test (NG)RC has largely passed with flying colors [2, 6, 8, 9, 13, 16, 17, 25, 41].”
BackgroundNishioka, D., Shingaya, Y., Tsuchiya, T., Higuchi, T., & Terabe, K. (2024) · Science Advances · doi:10.1126/sciadv.adk6438 · Cited by 37
“…performance due to its harnessing of the inherent nonlinear responses of physical dynamical systems, termed “physical reservoirs” in the framework of reservoir computing (RC), for mapping time-series data to high-dimensional feature space to achieve efficient information processing ( 4 , 5 ).”
Szymczyk, P., & Szymczyk, M. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.06.025 · Cited by 32
de Vos, N. J. (2013) · Hydrology and earth system sciences · doi:10.5194/hess-17-253-2013 · Cited by 36
“, 2002), ESNs (Jaeger, 2001; Jaeger and Haas, 2004) and Backpropagation-Decorrelation learning rule (Steil, 2004).”
BackgroundXu, X., & Ren, W. (2019) · Sustainability · doi:10.3390/su11113096 · Cited by 31
“In order to verify the e ff ectiveness of the proposed algorithm, the original model (ESN) [23], single-hidden layer feedforward network (SLFN) [41], extreme learning machine (ELM) [42], back propagation neural network (BPNN) [43], the least squares support vector machine (LSSVM) [44], and the long…”
MethodOpala, A., & Matuszewski, M. (2023) · Optical Materials Express · doi:10.1364/ome.496985 · Cited by 42
AI/ML for beyond 5G systems: Concepts, technology enablers & solutions
Taleb, T., Benzaïd, C., Addad, R. A., & Samdanis, K. (2023) · Computer Networks · doi:10.1016/j.comnet.2023.110044 · Cited by 46
Exploring quantumness in quantum reservoir computing
Götting, N., Lohof, F., & Gies, C. (2023) · Physical Review A · doi:10.1103/physreva.108.052427 · Cited by 47
Bai, Y., Deng, S., Pu, Z., & Li, C. (2024) · Energy · doi:10.1016/j.energy.2024.132338 · Cited by 32
Brain-inspired computing with self-assembled networks of nano-objects
Vahl, A., Milano, G., Kuncic, Z., Brown, S. A., & Milani, P. (2024) · Journal of Physics D Applied Physics · doi:10.1088/1361-6463/ad7a82 · Cited by 39
“RC represents a computational framework derived from recurrent neural network (RNN) models such as echo state networks [185] and liquid state machines [186] where computation is divided in two sections: the ‘reservoir’ and the ‘readout’ [187, 188].”
Integrated laser graded neuron enabling high-speed reservoir computing without a feedback loop
Nie, Y., Yang, B., Wang, D., Wang, T., Wang, J., Wang, Z., & Huang, C. (2024) · Optica · doi:10.1364/optica.537231 · Cited by 36
Physical reservoir computing: a tutorial
Stepney, S. (2024) · Natural Computing · doi:10.1007/s11047-024-09997-y · Cited by 57
“7.2.2), and channel equalisation (Mathews and Lee 1994; Jaeger and Haas 2004).”
InfluentialNajibi, E., & Rostami, H. (2015) · Applied Intelligence · doi:10.1007/s10489-015-0652-3 · Cited by 32
“But biological neural systems usually have sparse random connectivity, massive number of neurons, recurrent paths, and local modification of synaptic weights [8, 9] that are very different from those of most of the existing artificial neural network models.”
BackgroundInfluentialDistributions of covariances as a window into the operational regime of neuronal networksPreprint
Dahmen, D., Diesmann, M., & Helias, M. (2016) · JuSER (Forschungszentrum Jülich) · doi:10.48550/arxiv.1605.04153 · Cited by 34
Prediction of Air Pollution Concentration Based on mRMR and Echo State Network
Xu, X., & Ren, W. (2019) · Applied Sciences · doi:10.3390/app9091811 · Cited by 30
“[24] is a new type of recurrent neural network.”
BackgroundDiffractive Coupling For Photonic Networks: How Big Can We Go?
Maktoobi, S., Froehly, L., Andréoli, L., Porté, X., Jacquot, M., Larger, L., & Brunner, D. (2019) · IEEE Journal of Selected Topics in Quantum Electronics · doi:10.1109/jstqe.2019.2930454 · Cited by 34
“Recently, the field has been revitalized by a new neural network algorithm [7], which has resulted in numerous novel demonstrations of neural network computing based on photonic”
BackgroundDistributed Kerr Non-linearity in a Coherent All-Optical Fiber-Ring Reservoir Computer
Pauwels, J., Verschaffelt, G., Massar, S., & der Sande, G. V. (2019) · Frontiers in Physics · doi:10.3389/fphy.2019.00138 · Cited by 34
“high speed and low power, analogue photonic computing system based on the concept of reservoir computing (RC) [1, 2].”
BackgroundLow dimensional mid-term chaotic time series prediction by delay parameterized method
Guo, X., Sun, Y., & Ren, J. (2019) · Information Sciences · doi:10.1016/j.ins.2019.12.021 · Cited by 31
Model-size reduction for reservoir computing by concatenating internal states through time
Sakemi, Y., Morino, K., Leleu, T., & Aihara, K. (2020) · Scientific Reports · doi:10.1038/s41598-020-78725-0 · Cited by 37
“To investigate the effects (12) W 0 x(t), W out 1 x (1; t), .”
BackgroundRecent progress on excitation and manipulation of spin-waves in spin Hall nano-oscillators*
Li, L., Chen, L., Liu, R., & Du, Y. (2020) · Chinese Physics B · doi:10.1088/1674-1056/abaed5 · Cited by 33
“Recently, spin-torque memristors and nano-oscillators have been proposed to build artificial neural networks for applications of artificial intelligence (AI) because of their high-speed and low-power consumption[55-58].”
BackgroundChen, X., Weng, T., Yang, H., Gu, C., Zhang, J., & SMALL, M. P. (2020) · Physical review. E · doi:10.1103/physreve.102.033314 · Cited by 32
A brain-inspired computational model for spatio-temporal information processing
Lin, X., Zou, X., Ji, Z., Huang, T., Wu, S., & Mi, Y. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.05.015 · Cited by 31
TEACHING - Trustworthy autonomous cyber-physical applications through human-centred intelligence
Bacciu, D., Akarmazyan, S., Armengaud, E., Bacco, M., Bravos, G. N., Calandra, C., Carlini, E., Carta, A., Cassará, P., Coppola, M., et al. (2021) · IEEE International Conference on Omni-layer Intelligent Systems (COINS) · doi:10.1109/coins51742.2021.9524099 · Cited by 36
Kawase, T., Miyazaki, T., Kanno, T., Tadano, K., Nakajima, Y., & Kawashima, K. (2021) · Sensors and Materials · doi:10.18494/sam.2021.3345 · Cited by 33
Time-Delayed Reservoir Computing Based on a Two-Element Phased Laser Array for Image Identification
Huang, Y., Zhou, P., Yang, Y., Chen, T., & Li, N. (2021) · IEEE photonics journal · doi:10.1109/jphot.2021.3115598 · Cited by 31
A Hopf physical reservoir computer
Shougat, M. R. E. U., Li, X., Mollik, T., & Perkins, E. (2021) · Scientific Reports · doi:10.1038/s41598-021-98982-x · Cited by 36
An echo state network with attention mechanism for production prediction in reservoirs
Liu, Y., Shan, L., Yu, D., Zeng, L., & Yang, M. (2021) · Journal of Petroleum Science and Engineering · doi:10.1016/j.petrol.2021.109920 · Cited by 30
Efficient optical reservoir computing for parallel data processing
Bu, T., Zhang, H., Kumar, S., Jin, M., Kumar, P., & Huang, Y. (2022) · Optics Letters · doi:10.1364/ol.464288 · Cited by 33
Quantum reservoir computing in finite dimensions
Martínez‐Peña, R., & Ortega, J. (2023) · Physical review. E · doi:10.1103/physreve.107.035306 · Cited by 65
High speed human action recognition using a photonic reservoir computer
Picco, E., Antonik, P., & Massar, S. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.06.014 · Cited by 37
“Reservoir computing has been applied to a variety of problems, including for instance speech recognition [29] and time series prediction[26, 30].”
BackgroundA novel approach to minimal reservoir computing
Ma, H., Prosperino, D., & Rath, C. W. (2023) · Scientific Reports · doi:10.1038/s41598-023-39886-w · Cited by 41
“A reservoir computer (RC) 5,23,24 is an artificial recurrent neural network (RNN) that relies on a static network called reservoir .”
BackgroundIntegrated photonic reservoir computing with an all-optical readout
Ma, C., Kerrebrouck, J. V., Deng, H., Sackesyn, S., Gooskens, E., Bai, B., Dambre, J., & Bienstman, P. (2023) · Optics Express · doi:10.1364/oe.502354 · Cited by 33
“In this context, photonic reservoir computing (RC) [1, 2] has emerged as a promising computational architecture for optical information processing, offering next-generation high bandwidth, low latency, and low power consumption capabilities.”
BackgroundLiu, Y., Zhao, J., Wang, W., Yi-Ping, W. U., & Wei-Chang, C. H. E. N. (2009) · Acta Automatica Sinica · doi:10.3724/sp.j.1004.2009.00731 · Cited by 30
Makarov, V. A., Song, Y., Velárde, M. G., Hübner, D., & Cruse, H. (2008) · Biological Cybernetics · doi:10.1007/s00422-008-0221-5 · Cited by 30
A transfer learning framework for predicting the emotional content of generalized sound events
Ntalampiras, S. (2017) · The Journal of the Acoustical Society of America · doi:10.1121/1.4977749 · Cited by 35
Neural dynamics of emotion and cognition: From trajectories to underlying neural geometry
Pessoa, L. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.08.007 · Cited by 37
“er. The matrix 𝑾i is the input-to-reservoir matrix and the matrix 𝑾 specifies the within-reservoir weights, both of which are generated randomly, that is, they are not learned. For more details, see (Jaeger and Haas, 2004; Lukosevicius, 2012). A central objective of our study was to investigate reservoir computing for…”
BackgroundInfluentialEstébanez, I., Fischer, I., & Soriano, M. C. (2019) · Physical Review Applied · doi:10.1103/physrevapplied.12.034058 · Cited by 30
“While short-term chaotic time-series prediction was considered in the early work on RC by Jaeger and Haas [12], chaotic attractor replication has recently attracted significant attention [8,11].”
BackgroundYang, Y., Xin, Z., & Liu, X. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3003975 · Cited by 30
“To deal with these problems, new RNN named long short term memory (LSTM) [4] and echo state network (ESN) [5], [6] have been proposed.”
BackgroundMethodFeasibility of dopamine as a vector-valued feedback signal in the basal ganglia
Wärnberg, E., & Kumar, A. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2221994120 · Cited by 34
The computational power of the human brain
Gebicke‐Haerter, P. J. (2023) · Frontiers in Cellular Neuroscience · doi:10.3389/fncel.2023.1220030 · Cited by 41
“, 2002) or “echo-state machines” (Jaeger and Haas, 2004) have been constructed.”
Predictive sequence learning in the hippocampal formation
Chen, Y., Zhang, H., Cameron, M., & B, T. J. S. A. (2024) · Neuron · doi:10.1016/j.neuron.2024.05.024 · Cited by 48
Multimodal Laughter Detection in Natural Discourses
Scherer, S., Schwenker, F., Campbell, N., & Palm, G. (2009) · Human Centered Robot Systems, Cognition, Interaction, Technology · doi:10.1007/978-3-642-10403-9_12 · Cited by 42
“In the second approach Echo State Networks (ESN) [6], making use of the sequential characteristics of the modulation spectrum features that are scaled perceptually as MFCCs, are used.”
MethodEcho State Queueing Network: A new reservoir computing learning tool
Basterrech, S., & Rubino, G. (2013) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc.2013.6488435 · Cited by 30
“Finally, we present some experimental results and we end with some conclusions as well as a discussion regarding future lines of research.”
ResultMurakami, M., Kröger, B. J., Birkholz, P., & Triesch, J. (2015) · IEEE International Conference on Development and Learning (ICDL) · doi:10.1109/devlrn.2015.7346142 · Cited by 34
“This stage models the vowel babbling phase of infants up to the point when they have learnt to utter the vowels of their mother tongue.”
BackgroundEnaction, Embodiment, Evolutionary Robotics
Rohde, M. (2010) · Atlantis thinking machines · doi:10.2991/978-94-91216-34-3 · Cited by 38
Lun, S., Hu, H., & Yao, X. (2019) · Applied Soft Computing · doi:10.1016/j.asoc.2019.02.005 · Cited by 29
Hyperspectral image classification based on multiple reduced kernel extreme learning machine
Lv, F., & Han, M. (2019) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-019-00926-5 · Cited by 29
“…learning machine (ELM) [14, 15] or “non-iter-ative training” [6, 39] is drawing increasing focus of computational intelligence researchers, which can avoid the shortcomings of the usually used machine learning methods, i.e. slow convergence and high computational complexity [17, 19, 41, 44].”
BackgroundModeling IoT Equipment With Graph Neural Networks
Zhang, W., Zhang, Y., Xu, L. J., Zhou, J., Liu, Y., Gu, M., Liu, X., & Yang, S. (2019) · IEEE Access · doi:10.1109/access.2019.2902865 · Cited by 32
“Jaeger & Haas [28] proposed an echo state network (ESN), which randomly generated and predicted states and was used in some dynamic systems [29] [30].”
BackgroundOptical neural networks based on optical fiber-communication system
Cheng, T., Chou, D.-Y., Liu, C.-C., Chang, Y.-J., & Chen, C. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.07.051 · Cited by 29
Bayesian Optimisation of Large-scale Photonic Reservoir Computers
Antonik, P., Marsal, N., Brunner, D., & Rontani, D. (2021) · Cognitive Computation · doi:10.1007/s12559-020-09732-6 · Cited by 31
Accelerating photonic computing by bandwidth enhancement of a time‐delay reservoir
Estébanez, I., Schwind, J., Fischer, I., & Argyris, A. (2018) · Nanophotonics · doi:10.1515/nanoph-2020-0184 · Cited by 37
Banerjee, A., Hart, J. D., Roy, R., & Ott, E. (2021) · Physical Review X · doi:10.1103/physrevx.11.031014 · Cited by 40
AQI time series prediction based on a hybrid data decomposition and echo state networks
Liu, H., & Zhang, X. (2021) · Environmental Science and Pollution Research · doi:10.1007/s11356-021-14186-w · Cited by 31
“The details about the ESN can be found in Jaeger and Haas (2004).”
BackgroundAn Improved Bees Algorithm for Training Deep Recurrent Networks for Sentiment Classification
Zeybek, S., Pham, D. T., Koç, E., & Seçer, A. (2021) · Symmetry · doi:10.3390/sym13081347 · Cited by 35
“The first way to handle the VEG problem is to use newer types of RNN architectures such as Long-Short-Term Memory (LSTM) [8], Gated-Recurrent Units (GRUs) [9] and Echo-State-Networks (ESNs) [18].”
MethodZhou, J., Wang, J., Yang, C., Li, X., & Xie, Y. C. (2021) · Sensors · doi:10.3390/s21217271 · Cited by 29
“In particular, W outj is trained by the ridge regression algorithm [28] according to U trainj , W rj and is scaled by where α is the scaling range and 0 < α < 1. ρ is the spectral radius of W rj , and W 0 is a sparse matrix which is randomly generated.”
MethodRate chaos and memory lifetime in spiking neural networks
Klinshov, V. V., Kovalchuk, A. V., Franović, I., Perc, M., & Svetec, M. (2022) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2022.112011 · Cited by 31
Bauwens, I., Harkhoe, K. K., Bienstman, P., Verschaffelt, G., & der Sande, G. V. (2022) · Optics Express · doi:10.1364/oe.449508 · Cited by 29
Akiyama, T., & Tanaka, G. (2022) · IEEE Access · doi:10.1109/access.2022.3158755 · Cited by 33
“The first task is to predict chaotic time series data generated by the Lorenz system [2], [18], [19].”
BackgroundMethodPredicting the dynamical behaviors for chaotic semiconductor lasers by reservoir computing
Li, X., Sheng, B., & Zhang, M. (2022) · Optics Letters · doi:10.1364/ol.459638 · Cited by 29
Cucchi, M., Parker, D., Stavrinidou, E., Gkoupidenis, P., & Kleemann, H. (2023) · Advanced Materials · doi:10.1002/adma.202209516 · Cited by 33
Distributed Classifier Based on Genetically Engineered Bacterial Cell Cultures
Didovyk, A., Игоревич, К. О., Ivanchenko, M., Hasty, J., Huerta, R., & Tsimring, L. S. (2014) · ACS Synthetic Biology · doi:10.1021/sb500235p · Cited by 31
Fink, O., Zio, E., & Weidmann, U. (2015) · IEEE Transactions on Reliability · doi:10.1109/tr.2015.2424213 · Cited by 30
“the ESN is in extracting dynamics in the presented data [30].”
BackgroundMethodLi, G., Niu, P., Zhang, W., & Zhang, Y. (2012) · Knowledge-Based Systems · doi:10.1016/j.knosys.2012.04.019 · Cited by 29
New Millennium AI and the Convergence of History
Schmidhuber, J. (2007) · Studies in computational intelligence · doi:10.1007/978-3-540-71984-7_2 · Cited by 34
“Evolino-based LSTM can solve tasks that Echo State networks [37] cannot, and achieves higher accuracy in certain continuous function generation tasks than gradient-based LSTM, as well as other conventional gradient descent RNNs.”
BackgroundShort-Term Memory Capacity in Networks via the Restricted Isometry Property
Charles, A. S., Yap, H. L., & Rozell, C. J. (2014) · Neural Computation · doi:10.1162/neco_a_00590 · Cited by 32
“In contrast to previous work on ESNs that leverage nonlinear network computations for computational power (Jaeger & Haas, 2004), the present work uses a linear network and nonlinear computations for signal recovery.”
BackgroundResultSchneider, B., Dambre, J., & Bienstman, P. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2498763 · Cited by 33
“Powerful RC systems have since been designed and applied successfully to tasks such as robot control, speech recognition, or channel equalization [2], [8]–[10].”
MethodGrigoryeva, L., & Ortega, J. (2017) · Journal of Machine Learning Research · doi:10.48550/arxiv.1712.00754 · Cited by 88
Constructive Neural Network Learning
Lin, S.-B., Zeng, J., & Zhang, X. (2018) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2771463 · Cited by 29
Using Echo State Networks for Anomaly Detection in Underground Coal Mines
Obst, O., Wang, X. R., & Prokopenko, M. (2008) · ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1109/ipsn.2008.35 · Cited by 36
Index distribution of the Ginibre ensemble
Allez, R., Touboul, J., & Wainrib, G. (2014) · Journal of Physics A Mathematical and Theoretical · doi:10.1088/1751-8113/47/4/042001 · Cited by 29
Neural Manifold Modulated Continual Reinforcement Learning for Musculoskeletal Robots
Chen, J., Chen, Z., Yao, C., & Qiao, H. (2022) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2022.3231055 · Cited by 32
“Although the previous work of echo state network (ESN) has proved that the ESN has echo state property under the condition of || W || 2 1 [32], [33], this manuscript mainly has two distinctions of the proof and conclusion.”
BackgroundExtending dynamic memory of spiking neuron networks
Klinshov, V. V., Kovalchuk, A. V., Soloviev, I. A., Maslennikov, O. V., Franović, I., & Perc, M. (2024) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2024.114850 · Cited by 30
“A popular paradigm for understanding the information processing in the brain is the reservoir computing [17–21].”
Overcoming the coherence time barrier in quantum machine learning on temporal data
Hu, F., Khan, S. A., Bronn, N. T., Angelatos, G., Rowlands, G. E., Ribeill, G. J., & Türeci, H. E. (2024) · Nature Communications · doi:10.1038/s41467-024-51162-7 · Cited by 85
“Channel equalization aims to reconstruct a message streamed throughanoisy,non-linearanddistortingcommunicationchanneland has been employed in benchmarking reservoir computing architectures 11,14 as well as other machine learning algorithms 42,43 .”
BackgroundMethodInfluentialAutomated real-time method for ventricular heartbeat classification
Ortín, S., Soriano, M. C., Alfaras, M., & Mirasso, C. R. (2018) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2018.11.005 · Cited by 29
Richness of Deep Echo State Network Dynamics
Gallicchio, C., & Micheli, A. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20521-8_40 · Cited by 30
Degradation Estimation and Prediction of Electronic Packages Using Data-Driven Approach
Prisacaru, A., Gromala, P. J., Han, B., & Zhang, G. (2021) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3068681 · Cited by 28
Robust echo state network with sparse online learning
Yang, C., Nie, K., Qiao, J., & Wang, D. (2022) · Information Sciences · doi:10.1016/j.ins.2022.02.009 · Cited by 28
Predicting extreme events from data using deep machine learning: When and where
Jiang, J., Huang, Z., Grebogi, C., & Lai, Y. (2022) · Physical Review Research · doi:10.1103/physrevresearch.4.023028 · Cited by 31
Wang, P., Yin, Y., Deng, X., Bo, Y.-C., & Shao, W. (2022) · ISA Transactions · doi:10.1016/j.isatra.2022.04.014 · Cited by 28
Tanaka, H., Azhari, S., Usami, Y., Banerjee, D., Kotooka, T., Srikimkaew, O., Dang, T.-T., Murazoe, S., Oyabu, R., Kimizuka, K., et al. (2022) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/ac676a · Cited by 31
“RC is a special RNN case, as shown in figure 16(b); it was developed from echo-state networks (ESNs) [45, 46] and liquid-state machines [47] as its information-processing framework [48, 49].”
BackgroundGenerative complex networks within a dynamic memristor with intrinsic variability
Guo, Y., Duan, W., Liu, X., Wang, X., Wang, L., Duan, S., Ma, C., & Li, H. (2023) · Nature Communications · doi:10.1038/s41467-023-41921-3 · Cited by 36
“Accordingly, in constructing a theoretical model of reservoir, the random weights are routinely drawn from a uniform distribution over (- ε , ε ) which are then rescaled to a spectral radius less than unity 69,70 .”
Moiré Synaptic Transistor for Homogeneous-Architecture Reservoir Computing
王, P. 鹏. W., Chen, M., 谢, Y. 永. X., 潘, C. 晨. P., Watanabe, K., Taniguchi, T., 程, B. 斌. C., 梁, S.-J. 世. L., & 缪, F. 峰. M. (2023) · Chinese Physics Letters · doi:10.1088/0256-307x/40/11/117201 · Cited by 30
Reservoir computing for macroeconomic forecasting with mixed-frequency data
Ballarin, G., Δελλαπόρτας, Π., Grigoryeva, L., Hirt, M., van Huellen, S., & Ortega, J. (2023) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2023.10.009 · Cited by 52
Simple Deterministically Constructed Recurrent Neural Networks
Rodan, A., & Peter Tiňo, B. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15381-5_33 · Cited by 28
Experiments on autonomous Boolean networks
Rosin, D. P., Rontani, D., Gauthier, D. J., & Schöll, E. (2013) · Chaos An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/1.4807481 · Cited by 31
Applying the Hybrid Model of EMD, PSR, and ELM to Exchange Rates Forecasting
Yang, H., & Lin, H.-C. (2015) · Computational Economics · doi:10.1007/s10614-015-9549-9 · Cited by 28
“IMFs possess simple frequency components and strong correlations, and thus are easy and accurate to forecast (Jaeger and Haas 2004).”
BackgroundNeuronal stability in medial frontal cortex sets individual variability in decision-making
Kurikawa, T., Haga, T., Handa, T., Harukuni, R., & Fukai, T. (2018) · Nature Neuroscience · doi:10.1038/s41593-018-0263-5 · Cited by 32
Online learning control with Echo State Networks of an oil production platform
Jordanou, J. P., Antonelo, E. A., & Camponogara, E. (2019) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2019.06.011 · Cited by 34
Deng, L., & Pan, Y. (2020) · Journal of Petroleum Science and Engineering · doi:10.1016/j.petrol.2020.107981 · Cited by 30
Physical Deep Learning Based on Optimal Control of Dynamical Systems
Furuhata, G., Niiyama, T., & Sunada, S. (2021) · Physical Review Applied · doi:10.1103/physrevapplied.15.034092 · Cited by 32
Nonlinear transient computation
Crook, N. T. (2006) · Neurocomputing · doi:10.1016/j.neucom.2006.10.148 · Cited by 28
Levels and Types of Action Selection: The Action Selection Soup
Öztürk, P. (2009) · Adaptive Behavior · doi:10.1177/1059712309339854 · Cited by 28
“Jeannerod (1997) also argues for the existence of a hierarchy of motor representations so that the representations at the higher levels serve as constraints for the lower level motor representations.”
BackgroundEmbedding Bifurcations into Pneumatic Artificial Muscle
Akashi, N., Kuniyoshi, Y., Jo, T., Nishida, M., Sakurai, R., Wakao, Y., & Nakajima, K. (2024) · Advanced Science · doi:10.1002/advs.202304402 · Cited by 27
Ceni, A., & Gallicchio, C. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127966 · Cited by 35
Metadata
- Authors
- Jaeger, H., & Haas, H.
- Affiliations
- Constructor University (DE)
- Corresponding author
- Jaeger, Herbert
- Venue
- Science
- Published
- 2004-04-02
- Volume
- 304
- Issue
- 5667
- Pages
- 78-80
- ISSN
- 0036-8075 (ISSN-L)
- 1095-9203
- OpenAlex
- W2118706537
- Cited by
- 3,811
- References
- 18
- Citations by year
- 2026: 257 · 2025: 314 · 2024: 315 · 2023: 332 · 2022: 300 · 2021: 355 · 2020: 259 · 2019: 309 · 2018: 237 · 2017: 160 · 2016: 142 · 2015: 128 · 2014: 120 · 2013: 107 · 2012: 100
- FWCI
- 33.93
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Science (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Reservoir Computing
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Chaos control and synchronization
- Keywords
- echo state networks, chaotic time series prediction, recurrent neural networks, channel equalization, wireless communication, energy efficiency, reservoir computing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.