English

Consistency capacity of reservoir computers

Disordered Systems and Neural Networks 2021-05-31 v1 Emerging Technologies

Abstract

We study the propagation and distribution of information-carrying signals injected in dynamical systems serving as a reservoir computers. A multivariate correlation analysis in tailored replica tests reveals consistency spectra and capacities of a reservoir. These measures provide a high-dimensional portrait of the nonlinear functional dependence on the inputs. For multiple inputs a hierarchy of capacity measures characterizes the interference of signals from each source. For each input the time-resolved capacity forms a nonlinear fading memory profile. We illustrate the methodology with various types of echo state networks.

Keywords

Cite

@article{arxiv.2105.13473,
  title  = {Consistency capacity of reservoir computers},
  author = {Thomas Jüngling and Thomas Lymburn and Michael Small},
  journal= {arXiv preprint arXiv:2105.13473},
  year   = {2021}
}