Echo State Networks trained by Tikhonov least squares are L2(μ) approximators of ergodic dynamical systems

14 May 2020

Papers citing "Echo State Networks trained by Tikhonov least squares are L2(μ) approximators of ergodic dynamical systems"

9 / 9 papers shown

Title
On the emergence of numerical instabilities in Next Generation Reservoir Computing Edmilson Roque dos Santos Erik Bollt 29 0 0 01 May 2025
Unsupervised Learning in Echo State Networks for Input Reconstruction Taiki Yamada Yuichi Katori Kantaro Fujiwara 31 0 0 20 Jan 2025
Expressivity of Neural Networks with Random Weights and Learned Biases Ezekiel Williams Avery Hee-Woon Ryoo Thomas Jiralerspong Alexandre Payeur M. Perich Luca Mazzucato Guillaume Lajoie 31 2 0 01 Jul 2024
Universal Approximation of Linear Time-Invariant (LTI) Systems through RNNs: Power of Randomness in Reservoir Computing Shashank Jere Lizhong Zheng Karim A. Said Lingjia Liu 23 2 0 04 Aug 2023
Using Connectome Features to Constrain Echo State Networks Jacob Morra M. Daley 22 4 0 05 Jun 2022
Gradient-free optimization of chaotic acoustics with reservoir computing Francisco Huhn Luca Magri 13 19 0 17 Jun 2021
Next Generation Reservoir Computing D. Gauthier Erik Bollt Aaron Griffith W. A. S. Barbosa 11 386 0 14 Jun 2021
Learn to Synchronize, Synchronize to Learn Pietro Verzelli Cesare Alippi L. Livi 11 26 0 06 Oct 2020
Dimension reduction in recurrent networks by canonicalization Lyudmila Grigoryeva Juan-Pablo Ortega 18 19 0 23 Jul 2020