English

Robust Forecasting using Predictive Generalized Synchronization in Reservoir Computing

Computational Physics 2022-01-05 v5

Abstract

Reservoir computers (RC) are a form of recurrent neural network (RNN) used for forecasting timeseries data. As with all RNNs, selecting the hyperparameters presents a challenge when training onnew inputs. We present a method based on generalized synchronization (GS) that gives direction in designing and evaluating the architecture and hyperparameters of an RC. The 'auxiliary method' for detecting GS provides a computationally efficient pre-training test that guides hyperparameterselection. Furthermore, we provide a metric for RC using the reproduction of the input system's Lyapunov exponentsthat demonstrates robustness in prediction.

Keywords

Cite

@article{arxiv.2103.00362,
  title  = {Robust Forecasting using Predictive Generalized Synchronization in Reservoir Computing},
  author = {Jason A. Platt and Adrian S. Wong and Randall Clark and Stephen G. Penny and Henry D. I. Abarbanel},
  journal= {arXiv preprint arXiv:2103.00362},
  year   = {2022}
}

Comments

Full Version of arXiv:2102.08930

R2 v1 2026-06-23T23:34:38.750Z