Forecasting Using Reservoir Computing: The Role of Generalized Synchronization
Abstract
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.
Cite
@article{arxiv.2102.08930,
title = {Forecasting Using Reservoir Computing: The Role of Generalized Synchronization},
author = {Jason A. Platt and Adrian Wong and Randall Clark and Stephen G. Penny and Henry D. I. Abarbanel},
journal= {arXiv preprint arXiv:2102.08930},
year = {2021}
}
Comments
This is the Shortened Version of the Paper, the longer paper, Robust Forecasting through Generalized Synchronization in Reservoir Computing, can be found at arXiv:2103.00362