We explore the effect of structure and connection complexity on the dynamical behaviour of Reservoir Computers (RC). At present, considerable effort is taken to design and hand-craft physical reservoir computers. Both structure and physical complexity are often pivotal to task performance, however, assessing their overall importance is challenging. Using a recently proposed framework, we evaluate and compare the dynamical freedom (referring to quality) of neural network structures, as an analogy for physical systems. The results quantify how structure affects the range of behaviours exhibited by these networks. It highlights that high quality reached by more complex structures is often also achievable in simpler structures with greater network size. Alternatively, quality is often improved in smaller networks by adding greater connection complexity. This work demonstrates the benefits of using abstract behaviour representation, rather than evaluation through benchmark tasks, to assess the quality of computing substrates, as the latter typically has biases, and often provides little insight into the complete computing quality of physical systems.
@inproceedings(Dale++:2019:UCNC, author = "Matthew Dale and Jack Dewhirst and Simon O'Keefe and Angelika Sebald and Susan Stepney and Martin Trefzer", title = "The role of structure and complexity on Reservoir Computing quality", pages = "52-64", doi = "10.1007/978-3-030-19311-9_6", crossref = "UCNC:2019" ) @proceedings(UCNC:2019, title = "UCNC 2019, Tokyo, Japan, June 2019", booktitle = "UCNC 2019, Tokyo, Japan, June 2019", series = "LNCS", volume = 11493, publisher = "Springer", year = 2019 )