Reservoir Computing Benchmarks: a tutorial review and critique
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 13 of its 140 references that are in the map. First posted on arXiv 10 May 2024.
Builds on
13 of 140 references.
References · 13
- 2018Datasheets for Datasetscited by 1,386
- 2018Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networkscited by 155
- 2019Backpropagation Algorithms and Reservoir Computing in Recurrent Neural Networks for the Forecasting of Complex Spatiotemporal Dynamicscited by 134
- 2021Chaos as an interpretable benchmark for forecasting and data-driven modellingcited by 88
- 2019A Unifying Framework for Information Processing in Stochastically Driven Dynamical Systemscited by 16
- 2016Supervised Learning in Spiking Neural Networks with FORCE Trainingcited by 13
- 2020Model-Free Control of Dynamical Systems with Deep Reservoir Computingcited by 12
- 2021Exploiting Multiple Timescales in Hierarchical Echo State Networkscited by 11
- 2019SpaRCe: Improved Learning of Reservoir Computing Systems through Sparse Representationscited by 7
- 2021Signals to Spikes for Neuromorphic Regulated Reservoir Computing and EMG Hand Gesture Recognitioncited by 5
- 2019Data-driven Reconstruction of Nonlinear Dynamics from Sparse Observationcited by 4
- 2021Quantifying the Computational Capability of a Nanomagnetic Reservoir Computing Platform with Emergent Magnetization Dynamicscited by 4
1 more
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.
- 2025Growing Reservoirs with Developmental Graph Cellular Automatacited by 2
- 2025ChemReservoir -- An Open-Source Framework for Chemically-Inspired Reservoir Computingcited by 0
- 2026Bridging Biological Hearing and Neuromorphic Computing: End-to-End Time-Domain Audio Signal Processing with Reservoir Computingcited by 0
- 2026Bridging Biological Hearing and Neuromorphic Computing: End-to-End Time-Domain Audio Signal Processing with Reservoir Computing25 Mar 2026
- 2025Growing Reservoirs with Developmental Graph Cellular Automata11 Aug 2025
- 2025ChemReservoir -- An Open-Source Framework for Chemically-Inspired Reservoir Computing31 May 2025