In linear reservoir computing, dominant training modes approximate the Koopman eigenfunctions of the data-generating dynamical system, linking RC directly to DMD.
Emerging opportunities and challenges for the future of reservoir computing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On Dominant Manifolds in Reservoir Computing Networks
In linear reservoir computing, dominant training modes approximate the Koopman eigenfunctions of the data-generating dynamical system, linking RC directly to DMD.