Greedy layer-wise or module-wise training of neural networks is compelling in constrained
and on-device settings where memory is limited, as it circumvents a number of problems of …

The rapid growth of research in exploiting machine learning to predict chaotic systems has
revived a recent interest in Hamiltonian neural networks (HNNs) with physical constraints …

We consider the problem of unsupervised domain adaptation (UDA) between a source and
a target domain under conditional and label shift aka Generalized Target Shift (GeTarS) …

One of the most fundamental laws of physics is the principle of least action. Motivated by its
predictive power, we introduce a neuronal least-action principle for cortical processing of …

Normalizing Flows (NF) are powerful likelihood-based generative models that are able to
trade off between expressivity and tractability to model complex densities. A now well …

We propose a detector of adversarial samples that is based on the view of neural networks
as discrete dynamic systems. The detector tells clean inputs from abnormal ones by …

Although deep neural networks are well-known for their remarkable performance in tackling
complex tasks, their hunger for computational resources remains a significant hurdle, posing …

Deep learning has emerged as a powerful approach for modelling static data like images
and more recently for modelling dynamical systems like those underlying times series …

End-to-end backpropagation has a few shortcomings: it requires loading the entire model
during training, which can be impossible in constrained settings, and suffers from three …

The modeling of dynamical phenomena in geophysics and climate is based on a deep
understanding of the underlying physics, described in the form of PDEs, and on their …