Dynamical systems reconstruction
PulseAugur coverage of Dynamical systems reconstruction — every cluster mentioning Dynamical systems reconstruction across labs, papers, and developer communities, ranked by signal.
-
New minimal architecture outperforms DS models, tackles regime changes
Researchers have developed a novel, minimal architecture called DynaBase for zero-shot reconstruction of dynamical systems. This architecture, featuring a single-parameter piecewise affine map and a context selector, ca…
-
New method speeds up RNN training for chaotic systems by over 100x
Researchers have developed a novel method for training Recurrent Neural Networks (RNNs) on long time series data from chaotic dynamical systems. Their approach, detailed in a NeurIPS 2026 spotlight paper, combines DEER …
-
Time series modeling needs dynamical systems perspective, paper argues
A new position paper proposes that time series modeling should adopt a dynamical systems perspective to advance the field. The authors argue that most time series originate from underlying dynamical systems, and acknowl…