Kernel Rank and Generalization Rank are common measures used to characterise reservoir computing systems. However, there are some common issues in literature that make comparisons of these measures difficult, as well as both measures ideally requiring access to the reservoir state. Further, Generalization Rank has an inherent level of arbitrariness in its definition, as well as requiring a separate experiment to compute. This paper introduces the Relative Utilization and Comparative Generalization Measures, as part of the family of Entropy Transformation Measures, which address these issues while capturing similar information.
doi:10.1007/978-3-031-63742-1_9
@inproceedings(Griffin:2024-UCNC, author = "David Griffin and Susan Stepney", title = "Entropy Transformation Measures for Computational Capacity", pages = "119-133", doi = "10.1007/978-3-031-63742-1_9", crossref = "UCNC-2024" ) @proceedings(UCNC-2024, title = "UCNC 2024, Pohang, South Korea, June 2024", booktitle = "UCNC 2024, Pohang, South Korea, June 2024", series = "LNCS", volume = 14776, publisher = "Springer", year = 2024 )