Forecasting Using Reservoir Computing: The Role of Generalized Synchronization
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 5 of its 77 references that are in the map. First posted on arXiv 4 Feb 2021.
Builds on
5 of 77 references.
References · 5
- 2015A Critical Review of Recurrent Neural Networks for Sequence Learningcited by 224
- 2019Backpropagation Algorithms and Reservoir Computing in Recurrent Neural Networks for the Forecasting of Complex Spatiotemporal Dynamicscited by 134
- 2019Model-free prediction of spatiotemporal dynamical systems with recurrent neural networks: Role of network spectral radiuscited by 34
- 2018Rapid Time Series Prediction with a Hardware-Based Reservoir Computercited by 14
- 2019Machine Learning of Time Series Using Time-delay Embedding and Precision Annealingcited by 2
Built on by
Citing papers per year: 2021: 2.
2 papers.