8 papers
Topological Out-of-Domain Generalization in Dynamical Systems Reconstruction
Georg Trede, Charlotte Ricarda Doll, Elias Weber +1
Predicting the behavior of dynamical systems (DS) beyond the dynamical and parameter regimes observed in training is a pivotal and essentially unresolved problem in scientific ML.…
Position: A Dynamical Systems Perspective is Needed to Advance Time Series Modeling
Daniel Durstewitz, Christoph Jürgen Hemmer, Florian Hess +2
Time series (TS) modeling has come a long way from early statistical, mainly linear, approaches to the current trend in TS foundation models. With a lot of hype and industrial dema…
The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling
Andre Herz, Matthijs Pals, Daniel Durstewitz +1
Dynamical systems reconstruction (DSR) aims to learn surrogate models that capture the dynamics underlying time-series data. Reliably deploying these surrogates requires uncertaint…
Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction
Florian Hess, Florian Götz, Daniel Durstewitz
Reconstructing nonlinear dynamical systems (DS) from data (DSR) is a fundamental challenge in science and engineering, but it inherently relies on sequential models. Recent breakth…
Continuous-Time Piecewise-Linear Recurrent Neural Networks
Alena Brändle, Alena Brändle, Lukas Eisenmann +3
In dynamical systems reconstruction (DSR) we aim to recover the dynamical system (DS) underlying observed time series. Specifically, we aim to learn a generative surrogate model wh…
What Neuroscience Can Teach AI About Learning in Continuously Changing Environments
Daniel Durstewitz, Bruno Averbeck, Georgia Koppe
Modern AI models, such as large language models, are usually trained once on a huge corpus of data, potentially fine-tuned for a specific task, and then deployed with fixed paramet…