4 papers · 1 filter
RRAEDy: Adaptive Latent Linearization of Nonlinear Dynamical Systems
Jad Mounayer, Sebastian Rodriguez, Jerome Tomezyk +2
Most existing latent-space models for dynamical systems require fixing the latent dimension in advance, they rely on complex loss balancing to approximate linear dynamics, and they…
Application of Reduced-Order Models for Temporal Multiscale Representations in the Prediction of Dynamical Systems
Elias Al Ghazal, Jad Mounayer, Beatriz Moya +3
Modeling and predicting the dynamics of complex multiscale systems remains a significant challenge due to their inherent nonlinearities and sensitivity to initial conditions, as we…
Variational Rank Reduction Autoencoders
Jad Mounayer, Alicia Tierz, Jerome Tomezyk +2
Deterministic Rank Reduction Autoencoders (RRAEs) enforce by construction a regularization on the latent space by applying a truncated SVD. While this regularization makes Autoenco…
Rank Reduction Autoencoders
Jad Mounayer, Sebastian Rodriguez, Chady Ghnatios +2
The choice of an appropriate bottleneck dimension and the application of effective regularization are both essential for Autoencoders to learn meaningful representations from unlab…