Filters

2011 - 201912020 - 20221

More filters

2020 - 20232
Reset filters

Settings

Start date: 2020 × DDC: 004 × Subject: Machine learning × WGL Institute: PIK ×

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Master Memory Function for Delay-Based Reservoir Computers With Single-Variable Dynamics
    ([New York, NY] : IEEE, 2022) Köster, Felix; Yanchuk, Serhiy; Lüdge, Kathy
    We show that many delay-based reservoir computers considered in the literature can be characterized by a universal master memory function (MMF). Once computed for two independent parameters, this function provides linear memory capacity for any delay-based single-variable reservoir with small inputs. Moreover, we propose an analytical description of the MMF that enables its efficient and fast computation. Our approach can be applied not only to single-variable delay-based reservoirs governed by known dynamical rules, such as the Mackey–Glass or Stuart–Landau-like systems, but also to reservoirs whose dynamical model is not available.
  • Thumbnail Image
    Item
    Supermodeling by combining imperfect models
    (Amsterdam : Elsevier B.V., 2011) Selten, F.M.; Duane, G.S.; Wiegerinck, W.; Keenlyside, N.; Kurths, J.; Kocarev, L.
    SUMO (Supermodeling by combining imperfect models) is a three-year project funded under FET Open program with a starting date October, 1, 2010. We review some basic facts and findings of the SUMO project.