17 citations · 42 across the 13 of their papers we have counts for
10 papers · 1 filter
Learning Generalizable Reconstruction of High-Dimensional Neural Dynamics
Anima Kujur, Zahra Monfared
Accurate reconstruction of long-duration neural recordings is challenging because local field potentials (LFPs) are high-resolution, multichannel, transient, and variable across su…
Contrastive and Multi-Task Learning on Noisy Brain Signals with Nonlinear Dynamical Signatures
Sucheta Ghosh, Felix Dietrich, Zahra Monfared
We introduce a two-stage multitask learning framework for analyzing Electroencephalography (EEG) signals that integrates denoising, dynamical modeling, and representation learning.…
Detecting Invariant Manifolds in ReLU-Based RNNs
Lukas Eisenmann, Alena Brändle, Zahra Monfared +1
Recurrent Neural Networks (RNNs) have found widespread applications in machine learning for time series prediction and dynamical systems reconstruction, and experienced a recent re…
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…
Koopman-informed recurrent neural networks
Erik Lien Bolager, Ana Čukarska, Iryna Burak +2
Recurrent neural networks are a successful neural architecture for many time-dependent problems, including time series analysis, forecasting, and modeling of dynamical systems. In…
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…
Bifurcations and loss jumps in RNN training
Lukas Eisenmann, Zahra Monfared, Niclas Alexander Göring +1
Recurrent neural networks (RNNs) are popular machine learning tools for modeling and forecasting sequential data and for inferring dynamical systems (DS) from observed time series.…
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…
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…
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…