Emerging opportunities and challenges for the future of reservoir computing

Reservoir computing originates in the early 2000s, the core idea being to utilize dynamical systems as reservoirs (nonlinear generalizations of standard bases) to adaptively learn spatiotemporal features and hidden patterns in complex time series. Shown to have the potential of achieving higher-precision prediction in chaotic systems, those pioneering works led to a great amount of interest and follow-ups in the community of nonlinear dynamics and complex systems. To unlock the full capabilities of reservoir computing towards a fast, lightweight, and significantly more interpretable learning framework for temporal dynamical systems, substantially more research is needed. This Perspective intends to elucidate…

• NN
  National Natural Science Foundation of China

  Awards: 11925103, 2021SHZDZX0103
• FW
  Fonds Wetenschappelijk Onderzoek

  Awards: G006020N, G0H1422N
• SA
  Science and Technology Commission of Shanghai Municipality

  Awards: 22JC1402500, 2021SHZDZX0103, 22JC1401402
• H2
  Horizon 2020 Framework Programme

  Awards: 101070195, 871330, 101046329, 101017237, EU H2020, 101098717
• EA
  Engineering and Physical Sciences Research Council

  Award: EP/X025454/1