We explore the effect of connectivity and topology on the dynamical behaviour of Reservoir Computers. 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 developed 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 behavioural range of networks. It demonstrates how 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 dynamical behaviour to assess the quality of computing substrates, rather than evaluation through benchmark tasks that often provide a narrow and biased insight into the computing quality of physical systems.
doi:10.1007/s11047-020-09823-1 | extended version of UCNC conference paper
@article(Dale++:2020:NACO, author = "Matthew Dale and Simon O'Keefe and Angelika Sebald and Susan Stepney and Martin A. Trefzer", title = "Reservoir computing quality: connectivity and topology", journal = "Natural Computing", volume = 20, number = 2, pages = "127-143", doi = "10.1007/s11047-020-09823-1", year = 2021 )