Reservoir Computing Benchmarks: a tutorial review and critique
arXiv:2405.06561 · doi:10.1080/17445760.2025.2472211
Abstract
Reservoir Computing is an Unconventional Computation model to perform computation on various different substrates, such as recurrent neural networks or physical materials. The method takes a 'black-box' approach, training only the outputs of the system it is built on. As such, evaluating the computational capacity of these systems can be challenging. We review and critique the evaluation methods used in the field of reservoir computing. We introduce a categorisation of benchmark tasks. We review multiple examples of benchmarks from the literature as applied to reservoir computing, and note their strengths and shortcomings. We suggest ways in which benchmarks and their uses may be improved to the benefit of the reservoir computing community.
47 pp, 15 figures, 9 tables, review article
References in corpus (14)
- Recent Advances in Physical Reservoir Computing: A Review
- Optoelectronic Reservoir Computing
- Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
- All-optical Reservoir Computing
- Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
- Harnessing disordered quantum dynamics for machine learning
- High performance photonic reservoir computer based on a coherently driven passive cavity
- Supervised Learning in Spiking Neural Networks with FORCE Training
- Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
- A Substrate-Independent Framework to Characterise Reservoir Computers
- Exploiting Multiple Timescales in Hierarchical Echo State Networks
- Data-driven Reconstruction of Nonlinear Dynamics from Sparse Observation
- SpaRCe: Improved Learning of Reservoir Computing Systems through Sparse Representations
- Signals to Spikes for Neuromorphic Regulated Reservoir Computing and EMG Hand Gesture Recognition