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. 17858v1 Announce Type: cross Abstract: Reservoir computing exploits nonlinear dynamical systems to encode temporal inputs into high-dimensional state space representations.
By Mohab Abdalla, Damien Rontani
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
arXiv:2606. 09929v1 Announce Type: cross Abstract: Physical reservoir computing harnesses nonlinear mechanical dynamics but, by convention, freezes the substrate and trains only a linear readout, presuming the substrate is not usefully trainable.
By Caleb Munigety
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:2608. 16084v1 Announce Type: new Abstract: Neural autoregressive models have rapidly emerged as powerful emulators of high-dimensional chaotic systems, yet their long-term instability and error growth remain poorly understood, leading to ad-hoc solutions.
By Conrad Ainslie, Pedram Hassanzadeh, Michael W. Mahoney, Ashesh Chattopadhyay
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
LoRA-RC introduces a low‑rank adaptation scheme for reservoir computing that updates the recurrent matrix using streaming prediction errors while keeping the base reservoir and adaptation bases fixed offline. The method projects a small core matrix onto a spectral‑norm ball and applies low‑pass filtering at each step, ensuring every recurrent matrix stays within a certified contraction set. Experiments on a Lorenz system with abrupt parameter drift show that LoRA‑RC reduces post‑drift prediction error by 56% compared to a fixed RC and 51% compared to readout‑only adaptation, and that removing the projection increases error by more than a factor of 40.
By Wenbin Wan
Echo State Networks (ESNs) offer an efficient framework for temporal prediction, but their randomly initialized reservoirs are often over-parameterized and dynamically redundant. Existing pruning methods largely rely on static connectivity or activation statistics, which may overlook neurons that shape input-driven state transitions.
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: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:2607. 07978v1 Announce Type: cross Abstract: Quantum reservoir computing uses a fixed quantum circuit as a feature generator and trains only a simple linear readout on top of it.
By Tushar Pandey