paper-with-me

홈 › Papers

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

2020-05-14 · Allen G Hart, James L Hook, Jonathan H P Dawes

Echo State Networks (ESNs) are a class of single-layer recurrent neural networks with randomly generated internal weights, and a single layer of tuneable outer weights, which are usually trained by regularised linear least squares regression. Remarkably, ESNs still enjoy the universal approximation property despite the training procedure being entirely linear. In this paper, we prove that an ESN trained on a sequence of observations from an ergodic dynamical system (with invariant measure $\mu$) using Tikhonov least squares regression against a set of targets, will approximate the target function in the $L^2(\mu)$ norm. In the special case that the targets are future observations, the ESN is learning the next step map, which allows time series forecasting. We demonstrate the theory numerically by training an ESN using Tikhonov least squares on a sequence of scalar observations of the Lorenz system.

📄 PDF Abstract BibTeX arXiv:2005.06967

Code (0)

등록된 구현이 없습니다.

Tasks

regressionTime SeriesTime Series AnalysisTime Series Forecasting

Similar Papers 제목 키워드 기반

Variance reduction in stochastic methods for large-scale regularised least-squares problems

2021-10-15 · Yusuf Pilavci, Pierre-Olivier Amblard, Simon Barthelmé, Nicolas Tremblay

Large dimensional least-squares and regularised least-squares problems are expensive to solve. There exist many approximate techniques, some deterministic (like conjugate gradient), some stochastic (like stochastic gradi…

Point Processes

Comparison of echo state network output layer classification methods on noisy data

2017-03-13 · Ashley Prater

Echo state networks are a recently developed type of recurrent neural network where the internal layer is fixed with random weights, and only the output layer is trained on specific data. Echo state networks are increasi…

Event DetectionGeneral Classificationspeech-recognitionSpeech Recognition

Beyond Tikhonov: Faster Learning with Self-Concordant Losses via Iterative Regularization

2021-06-16 · NeurIPS 2021 12 · Gaspard Beugnot, Julien Mairal, Alessandro Rudi

The theory of spectral filtering is a remarkable tool to understand the statistical properties of learning with kernels. For least squares, it allows to derive various regularization schemes that yield faster convergence…

Beyond Tikhonov: faster learning with self-concordant losses, via iterative regularization

2021-05-21 · NeurIPS 2021 12 · Gaspard Beugnot, Julien Mairal, Alessandro Rudi

The theory of spectral filtering is a remarkable tool to understand the statistical properties of learning with kernels. For least squares, it allows to derive various regularization schemes that yield faster convergence…

Recursive Least Squares Policy Control with Echo State Network

2022-01-13 · Chunyuan Zhang, Chao Liu, Qi Song, Jie Zhao

The echo state network (ESN) is a special type of recurrent neural networks for processing the time-series dataset. However, limited by the strong correlation among sequential samples of the agent, ESN-based policy contr…

Time SeriesTime Series Analysis