Transformers fail to predict catastrophic collapse in unseen parameter regimes of nonlinear dynamical systems, while reservoir computing reliably succeeds.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Reservoir computing on NMF-reduced spatiotemporal data predicts tipping times within narrow windows for dynamical systems and CMIP5 climate projections.
Reservoir observers enhanced by residual calibration and attention substantially raise inference accuracy on chaotic systems, especially in previously worst-case input scenarios.
citing papers explorer
-
Can Transformers predict system collapse in dynamical systems?
Transformers fail to predict catastrophic collapse in unseen parameter regimes of nonlinear dynamical systems, while reservoir computing reliably succeeds.
-
Anticipating tipping in spatiotemporal systems with machine learning
Reservoir computing on NMF-reduced spatiotemporal data predicts tipping times within narrow windows for dynamical systems and CMIP5 climate projections.
-
Reservoir observer enhanced with residual calibration and attention mechanism
Reservoir observers enhanced by residual calibration and attention substantially raise inference accuracy on chaotic systems, especially in previously worst-case input scenarios.