2021/05/25 by Thomas Jüngling, Jüngling, Thomas, Thomas Lymburn +3 · 1 citation
Computer Science · Engineering · Physics and Astronomy · #Advanced Memory and Neural Computing #Disordered Systems and Neural Networks (cond-mat.dis-nn) #Emerging Technologies (cs.ET) #FOS: Computer and information sciences #FOS: Physical sciences #Neural Networks and Applications #Neural Networks and Reservoir Computing #cond-mat.dis-nn #cs.ET
paper · pdf · doi:10.48550/arxiv.2105.13473
arxiv created 2021/05/25 · openalex publication_date 2021/05/25 · arxiv updated 2021/05/31 · openalex created_date 2021/06/07 · openalex updated_date 2026/07/28
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.