Robust Forecasting using Predictive Generalized Synchronization in Reservoir Computing

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.

Full Version of arXiv:2102.08930

References in corpus (3)

• On the difficulty of training Recurrent Neural Networks
• Forecasting Chaotic Systems with Very Low Connectivity Reservoir Computers
• Do Reservoir Computers Work Best at the Edge of Chaos?

Cited by in corpus (4)

• Next Generation Reservoir Computing
• Catch-22s of reservoir computing
• Role of assortativity in predicting burst synchronization using echo state network
• Learning Beyond Experience: Generalizing to Unseen State Space with Reservoir Computing