80 citations · 292 across the 14 of their papers we have counts for
16 papers
Generalized Teacher Forcing for Learning Chaotic Dynamics
Florian Hess, Zahra Monfared, Manuel Brenner +1
Chaotic dynamical systems (DS) are ubiquitous in nature and society. Often we are interested in reconstructing such systems from observed time series for prediction or mechanistic…
Integrating Multimodal Data for Joint Generative Modeling of Complex Dynamics
Manuel Brenner, Florian Hess, Georgia Koppe +1
Many, if not most, systems of interest in science are naturally described as nonlinear dynamical systems. Empirically, we commonly access these systems through time series measurem…
Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systems
Manuel Brenner, Florian Hess, Jonas M. Mikhaeil +4
In many scientific disciplines, we are interested in inferring the nonlinear dynamical system underlying a set of observed time series, a challenging task in the face of chaotic be…
Reconstructing Nonlinear Dynamical Systems from Multi-Modal Time Series
Daniel Kramer, Philine Lou Bommer, Carlo Tombolini +2
Empirically observed time series in physics, biology, or medicine, are commonly generated by some underlying dynamical system (DS) which is the target of scientific interest. There…
On the difficulty of learning chaotic dynamics with RNNs
Jonas M. Mikhaeil, Zahra Monfared, Daniel Durstewitz
Recurrent neural networks (RNNs) are wide-spread machine learning tools for modeling sequential and time series data. They are notoriously hard to train because their loss gradient…
Transformation of ReLU-based recurrent neural networks from discrete-time to continuous-time
Zahra Monfared, Daniel Durstewitz
Recurrent neural networks (RNN) as used in machine learning are commonly formulated in discrete time, i.e. as recursive maps. This brings a lot of advantages for training models on…