Forecasting Using Reservoir Computing: The Role of Generalized Synchronization

02/04/2021 ∙ by Jason A. Platt, et al. ∙ 0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.