Optimizing reservoir computing by minimizing error in the reconstructed invariant distribution reproduces Lyapunov exponents and chaotic attractors more reliably than maximizing prediction time.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
nlin.CD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Optimizing Reservoir Computing for Reconstructing Ergodic Properties
Optimizing reservoir computing by minimizing error in the reconstructed invariant distribution reproduces Lyapunov exponents and chaotic attractors more reliably than maximizing prediction time.