Optimal reservoir computers for forecasting systems of nonlinear dynamics

• URL: http://arxiv.org/abs/2202.05159v1
• Date: Wed, 9 Feb 2022 09:36:31 GMT
• Title: Optimal reservoir computers for forecasting systems of nonlinear dynamics
• Authors: Pauliina K\"arkk\"ainen and Riku Linna
• Abstract summary: We show that reservoirs of low connectivity perform better than or as well as those of high connectivity in forecasting noiseless Lorenz and coupled Wilson-Cowan systems. We also show that, unexpectedly, computationally effective reservoirs of unconnected nodes (RUN) outperform reservoirs of linked network topologies in predicting these systems.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Prediction and analysis of systems of nonlinear dynamics is crucial in many applications. Here, we study characteristics and optimization of reservoir computing, a machine learning technique that has gained attention as a suitable method for this task. By systematically applying Bayesian optimization on reservoirs we show that reservoirs of low connectivity perform better than or as well as those of high connectivity in forecasting noiseless Lorenz and coupled Wilson-Cowan systems. We also show that, unexpectedly, computationally effective reservoirs of unconnected nodes (RUN) outperform reservoirs of linked network topologies in predicting these systems. In the presence of noise, reservoirs of linked nodes perform only slightly better than RUNs. In contrast to previously reported results, we find that the topology of linked reservoirs has no significance in the performance of system prediction. Based on our findings, we give a procedure for designing optimal reservoir computers (RC) for forecasting dynamical systems. This work paves way for computationally effective RCs applicable to real-time prediction of signals measured on systems of nonlinear dynamics such as EEG or MEG signals measured on a brain.

Related papers

• Tailored minimal reservoir computing: on the bidirectional connection between nonlinearities in the reservoir and in data [0.0]
  We study how the degree of nonlinearity in the input data affects the optimal design of reservoir computers. By reducing minimal RCs to a single tunable nonlinearity parameter, we explore how the predictive performance varies with the degree of nonlinearity in the reservoir. Our experiments reveal that the prediction performance is maximized when the reservoir's nonlinearity matches the nonlinearity present in the data.
  arXiv  Detail & Related papers  (2025-04-24T12:47:21Z)
• Denoising and Reconstruction of Nonlinear Dynamics using Truncated Reservoir Computing [0.0]
  This paper presents a novel Reservoir Computing (RC) method for noise filtering and reconstructing nonlinear dynamics. The performance of the RC in terms of noise intensity, noise frequency content, and drastic shifts in dynamical parameters are studied. It is shown that the denoising performance improves via truncating redundant nodes and edges of the computing reservoir.
  arXiv  Detail & Related papers  (2025-04-17T21:47:13Z)
• Efficient Transformed Gaussian Process State-Space Models for Non-Stationary High-Dimensional Dynamical Systems [49.819436680336786]
  We propose an efficient transformed Gaussian process state-space model (ETGPSSM) for scalable and flexible modeling of high-dimensional, non-stationary dynamical systems. Specifically, our ETGPSSM integrates a single shared GP with input-dependent normalizing flows, yielding an expressive implicit process prior that captures complex, non-stationary transition dynamics. Our ETGPSSM outperforms existing GPSSMs and neural network-based SSMs in terms of computational efficiency and accuracy.
  arXiv  Detail & Related papers  (2025-03-24T03:19:45Z)
• Synergistic Development of Perovskite Memristors and Algorithms for Robust Analog Computing [53.77822620185878]
  We propose a synergistic methodology to concurrently optimize perovskite memristor fabrication and develop robust analog DNNs. We develop "BayesMulti", a training strategy utilizing BO-guided noise injection to improve the resistance of analog DNNs to memristor imperfections. Our integrated approach enables use of analog computing in much deeper and wider networks, achieving up to 100-fold improvements.
  arXiv  Detail & Related papers  (2024-12-03T19:20:08Z)
• Deep Recurrent Stochastic Configuration Networks for Modelling Nonlinear Dynamic Systems [3.8719670789415925]
  This paper proposes a novel deep reservoir computing framework, termed deep recurrent configuration network (DeepRSCN) DeepRSCNs are incrementally constructed, with all reservoir nodes directly linked to the final output. Given a set of training samples, DeepRSCNs can quickly generate learning representations, which consist of random basis functions with cascaded input readout weights.
  arXiv  Detail & Related papers  (2024-10-28T10:33:15Z)
• Higher order quantum reservoir computing for non-intrusive reduced-order models [0.0]
  Quantum reservoir computing technique (QRC) is a hybrid quantum-classical framework employing an ensemble of interconnected small quantum systems. We show that QRC is able to predict complex nonlinear dynamical systems in a stable and accurate manner.
  arXiv  Detail & Related papers  (2024-07-31T13:37:04Z)
• Feature-Based Echo-State Networks: A Step Towards Interpretability and Minimalism in Reservoir Computer [0.0]
  This paper proposes a novel and interpretable recurrent neural-network structure using the echo-state network (ESN) paradigm for time-series prediction. A systematic reservoir architecture is developed using smaller parallel reservoirs driven by different input combinations, known as features. The resultant feature-based ESN (Feat-ESN) outperforms the traditional single-reservoir ESN with less reservoir nodes.
  arXiv  Detail & Related papers  (2024-03-28T19:41:17Z)
• Hallmarks of Optimization Trajectories in Neural Networks: Directional Exploration and Redundancy [75.15685966213832]
  We analyze the rich directional structure of optimization trajectories represented by their pointwise parameters. We show that training only scalar batchnorm parameters some while into training matches the performance of training the entire network.
  arXiv  Detail & Related papers  (2024-03-12T07:32:47Z)
• EASRec: Elastic Architecture Search for Efficient Long-term Sequential Recommender Systems [82.76483989905961]
  Current Sequential Recommender Systems (SRSs) suffer from computational and resource inefficiencies. We develop the Elastic Architecture Search for Efficient Long-term Sequential Recommender Systems (EASRec) EASRec introduces data-aware gates that leverage historical information from input data batch to improve the performance of the recommendation network.
  arXiv  Detail & Related papers  (2024-02-01T07:22:52Z)
• Excitatory/Inhibitory Balance Emerges as a Key Factor for RBN Performance, Overriding Attractor Dynamics [35.70635792124142]
  Reservoir computing provides a time and cost-efficient alternative to traditional learning methods. We show that specific distribution parameters can lead to diverse dynamics near critical points. We then evaluate performance in two challenging tasks, memorization and prediction, and find that a positive excitatory balance produces a critical point with higher memory performance.
  arXiv  Detail & Related papers  (2023-08-02T17:41:58Z)
• Controlling dynamical systems to complex target states using machine learning: next-generation vs. classical reservoir computing [68.8204255655161]
  Controlling nonlinear dynamical systems using machine learning allows to drive systems into simple behavior like periodicity but also to more complex arbitrary dynamics. We show first that classical reservoir computing excels at this task. In a next step, we compare those results based on different amounts of training data to an alternative setup, where next-generation reservoir computing is used instead. It turns out that while delivering comparable performance for usual amounts of training data, next-generation RC significantly outperforms in situations where only very limited data is available.
  arXiv  Detail & Related papers  (2023-07-14T07:05:17Z)
• Optimization of a Hydrodynamic Computational Reservoir through Evolution [58.720142291102135]
  We interface with a model of a hydrodynamic system, under development by a startup, as a computational reservoir. We optimized the readout times and how inputs are mapped to the wave amplitude or frequency using an evolutionary search algorithm. Applying evolutionary methods to this reservoir system substantially improved separability on an XNOR task, in comparison to implementations with hand-selected parameters.
  arXiv  Detail & Related papers  (2023-04-20T19:15:02Z)
• On the Effective Usage of Priors in RSS-based Localization [56.68864078417909]
  We propose a Received Signal Strength (RSS) fingerprint and convolutional neural network-based algorithm, LocUNet. In this paper, we study the localization problem in dense urban settings. We first recognize LocUNet's ability to learn the underlying prior distribution of the Rx position or Rx and transmitter (Tx) association preferences from the training data, and attribute its high performance to these.
  arXiv  Detail & Related papers  (2022-11-28T00:31:02Z)
• Large-Scale Sequential Learning for Recommender and Engineering Systems [91.3755431537592]
  In this thesis, we focus on the design of an automatic algorithms that provide personalized ranking by adapting to the current conditions. For the former, we propose novel algorithm called SAROS that take into account both kinds of feedback for learning over the sequence of interactions. The proposed idea of taking into account the neighbour lines shows statistically significant results in comparison with the initial approach for faults detection in power grid.
  arXiv  Detail & Related papers  (2022-05-13T21:09:41Z)
• Model-Free Prediction of Chaotic Systems Using High Efficient Next-generation Reservoir Computing [4.284497690098487]
  A new paradigm of reservoir computing is proposed for achieving model-free predication for both low-dimensional and large chaotic systems. By taking the Lorenz and Kuramoto-Sivashinsky equations as two classical examples of dynamical systems, numerical simulations are conducted. The results show our model excels at predication tasks than the latest reservoir computing methods.
  arXiv  Detail & Related papers  (2021-10-19T12:49:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.