Abstract The use of Machine Learning (ML) has rapidly spread across several fields of
applied sciences, having encountered many applications in Structural Dynamics and …

The combination of ordinary differential equations and neural networks, ie, neural ordinary
differential equations (Neural ODE), has been widely studied from various angles. However …

While significant progress has been made on Physics-Informed Neural Networks (PINNs), a
comprehensive comparison of these methods across a wide range of Partial Differential …

Deep learning models, though having achieved great success in many different fields over
the past years, are usually data-hungry, fail to perform well on unseen samples, and lack …

Deep learning has been widely used within learning algorithms for robotics. One
disadvantage of deep networks is that these networks are black-box representations …

Modern applications increasingly require learning and forecasting latent dynamics from high-
dimensional time-series. Compared to univariate time-series forecasting, this adds a new …

Many real-world dynamical systems are associated with first integrals (aka invariant
quantities), which are quantities that remain unchanged over time. The discovery and …

We propose a new model class aimed at predicting dynamical trajectories from high-
dimensional empirical data. This is done by combining variational autoencoders and (spatio …

We propose a method for learning dynamical systems from high-dimensional empirical data
that combines variational autoencoders and (spatio-) temporal attention within a framework …

Even though a variety of methods have been proposed in the literature, efficient and
effective latent-space control (ie, control in a learned low-dimensional space) of physical …