paper-with-me

Papers

Forecasting Using Reservoir Computing: The Role of Generalized Synchronization

2021-02-04 · Jason A. Platt, Adrian Wong, Randall Clark, Stephen G. Penny, Henry D. I. Abarbanel

Reservoir computers (RC) are a form of recurrent neural network (RNN) used for forecasting time series data. As with all RNNs, selecting the hyperparameters presents a challenge when training on new inputs. We present a method based on generalized synchronization (GS) that gives direction in designing and evaluating the architecture and hyperparameters of a RC. The 'auxiliary method' for detecting GS provides a pre-training test that guides hyperparameter selection. Furthermore, we provide a metric for a "well trained" RC using the reproduction of the input system's Lyapunov exponents.

📄 PDF Abstract BibTeX arXiv:2102.08930

Code (0)

등록된 구현이 없습니다.

Tasks

Time SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

Adaptive Reservoir Computing for Multi-Scenario Chaotic System Forecasting

2026-05-27 · Shadmehr Zaregarizi, Khashayar Yavari arxiv

We present an adaptive reservoir computing framework for the CTF-4-Science Lorenz benchmark, which evaluates machine learning models across twelve distinct tasks spanning five qualitatively different scenarios: baseline …

Few-Shot Learning

Reservoir Computing using High Order Synchronization of Coupled Oscillators

2020-04-08 · A. A. Velichko, D. V. Ryabokon, S. D. Khanin, A. V. Sidorenko 외

We propose a concept for reservoir computing on oscillators using the high-order synchronization effect. The reservoir output is presented in the form of oscillator synchronization metrics: fractional high-order synchron…

FormVocal Bursts Intensity Prediction

Learn to Synchronize, Synchronize to Learn

2020-10-06 · Pietro Verzelli, Cesare Alippi, Lorenzo Livi

In recent years, the machine learning community has seen a continuous growing interest in research aimed at investigating dynamical aspects of both training procedures and machine learning models. Of particular interest …

BIG-bench Machine Learning

Quantitative evaluation of the performance of discrete-time reservoir computers in the forecasting, filtering, and reconstruction of stochastic stationary signals

2015-08-01 · Lyudmila Grigoryeva, Julie Henriques, Juan-Pablo Ortega

This paper extends the notion of information processing capacity for non-independent input signals in the context of reservoir computing (RC). The presence of input autocorrelation makes worthwhile the treatment of forec…

Time SeriesTime Series Analysisvalid

Attractor reconstruction with reservoir computers: The effect of the reservoir's conditional Lyapunov exponents on faithful attractor reconstruction

2023-12-30 · Joseph D. Hart

Reservoir computing is a machine learning framework that has been shown to be able to replicate the chaotic attractor, including the fractal dimension and the entire Lyapunov spectrum, of the dynamical system on which it…