The paper investigates how training shapes the geometry of recurrent network dynamics in Reservoir Computing (RC) networks used for temporal forecasting. It demonstrates that, in a linear continuous-time reservoir with infinite data, training data create an invariant subspace whose dimension matches the number of dominant modes. For a simplified diagonal linear reservoir, the study connects dominant eigenvalues and eigenvectors to the spectrum of a backward Dynamic Mode Decomposition matrix, providing a finite-dimensional approximation of the backward-time Koopman operator, and illustrates these phenomena through simulation while suggesting extensions to nonlinear RC.
By Noa Kaplan, Alberto Padoan, Anastasia Bizyaeva
arXiv:2607. 24420v1 Announce Type: cross Abstract: Reservoir computing has emerged as an efficient machine learning framework for predicting time series generated by dynamical systems.
By Arthur S Powanwe
arXiv:2607. 17909v1 Announce Type: cross Abstract: The edge-of-chaos heuristic has long served as a guiding principle for designing reservoir computers, yet its relevance to machine performance remains elusive.
By Yao Du, Xingang Wang
arXiv:2504. 17503v2 Announce Type: replace Abstract: We study how the degree of nonlinearity in the input data affects the optimal design of reservoir computers, focusing on how closely the model's nonlinearity should align with that of the data.
By Davide Prosperino, Haochun Ma, Christoph R\"ath
The paper introduces task‑resolved Fisher spectroscopy for quantum reservoir computing, defining orthonormal score coordinates from prediction targets that reweight labeled histories to produce an affine family of reservoir states and measurement outcomes. It establishes a Fisher‑information hierarchy linking state quantum Fisher information, measurement record Fisher information, and moment matrices up to many‑body order, providing a quadratic form that equals the stationary capacity of the optimal linear readout. The method requires only stationary labeled records and measured outcomes, enabling predictions of held‑out capacities, necessary feature order, and measurement‑budget dependence, and demonstrates how optimizing local measurement axes can recover hidden task information in a five‑spin open reservoir.
By Yang Peng
arXiv:2606. 19984v1 Announce Type: new Abstract: Reservoir computing offers a lightweight framework for forecasting dynamical systems but may struggle to capture long-range dependencies due to limited representational capacity.
By Juntian Huang, Jurgen Kurths, Ying Tang
arXiv:2608. 04028v1 Announce Type: cross Abstract: Echo-state networks enable efficient temporal learning by fixing the recurrent dynamics and training only a linear readout.
By Jyotiranjan Beuria, Amit Shukla
arXiv:2505. 17740v2 Announce Type: replace Abstract: Making accurate predictions of chaotic time series is a complex challenge.
By Rodrigo Mart\'inez-Pe\~na, Rom\'an Or\'us
arXiv:2404. 17429v4 Announce Type: replace-cross Abstract: A natural hypothesis for the success of reservoir computing in generic tasks is the ability of the untrained reservoir to map distinct input time series to separable reservoir states, a property we term separation capacity.
By Youness Boutaib
The paper studies how reservoir‑computing associative memories can reliably recall dynamical memories even when their basins of attraction are riddled and unpredictable. It finds that these basins have an octopus‑like shape, with a robust head near the attractor and thin, intertwined tentacles that span state space. By using cue‑driven generalized synchronization, the system bypasses the unpredictable tentacular regions and is driven into the robust basin head, establishing a quantitative link between cue duration, synchronization rate, and basin‑head radius.
By Ling-Wei Kong, Ying-Cheng Lai
arXiv:2608. 04593v1 Announce Type: cross Abstract: Echo State Networks (ESNs) offer an efficient framework for temporal prediction, but their randomly initialized reservoirs are often over-parameterized and dynamically redundant.
By Sudip Laudari, Puspa Raj Adhikari
arXiv:2509. 24122v3 Announce Type: replace Abstract: At the heart of time-series forecasting (TSF) lies a fundamental challenge: how can models efficiently and effectively capture long-range temporal dependencies across ever-growing sequences?
By Hongbo Liu, Jia Xu