5 papers · 1 filter
Uncovering the Computational Roles of Nonlinearity in Sequence Modeling Using Almost-Linear RNNs
Manuel Brenner, Georgia Koppe
Sequence modeling tasks across domains such as natural language processing, time series forecasting, and control require learning complex input-output mappings. Nonlinear recurrenc…
Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data
Manuel Brenner, Elias Weber, Georgia Koppe +1
In science, we are often interested in obtaining a generative model of the underlying system dynamics from observed time series. While powerful methods for dynamical systems recons…
Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction
Manuel Brenner, Christoph Jürgen Hemmer, Zahra Monfared +1
Dynamical systems (DS) theory is fundamental for many areas of science and engineering. It can provide deep insights into the behavior of systems evolving in time, as typically des…
Optimal Recurrent Network Topologies for Dynamical Systems Reconstruction
Christoph Jürgen Hemmer, Manuel Brenner, Florian Hess +1
In dynamical systems reconstruction (DSR) we seek to infer from time series measurements a generative model of the underlying dynamical process. This is a prime objective in any sc…
Out-of-Domain Generalization in Dynamical Systems Reconstruction
Niclas Göring, Florian Hess, Manuel Brenner +2
In science we are interested in finding the governing equations, the dynamical rules, underlying empirical phenomena. While traditionally scientific models are derived through cycl…