The paper derives a sufficient Lyapunov-based stability radius for reservoir computers and shows numerically that training error is low in the predicted globally stable parameter region, provided the node polynomial contains both an odd and an even power term.
a ger, Wolfgang Maass, and Henry Markram. The
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Stability Analysis of Reservoir Computers Dynamics via Lyapunov Functions
The paper derives a sufficient Lyapunov-based stability radius for reservoir computers and shows numerically that training error is low in the predicted globally stable parameter region, provided the node polynomial contains both an odd and an even power term.