Our latest paper, reviewing a bunch of standard benchmarks for Reservoir Computing, digging into their histories, and why some of them might not be the best approach to be using.
Chester Wringe, Martin Trefzer, Susan Stepney. Reservoir computing benchmarks: a tutorial review and critique. International Journal of Parallel, Emergent and Distributed Systems, 1-39, 2025. doi:10.1080/17445760.2025.2472211
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.
If you don't subscribe to that journal, you can find the same text (if not as prettily typeset) on the arXiv, at arXiv:2405.06561 [cs.ET]
No comments:
Post a Comment