11 citations · 16 across the 6 of their papers we have counts for
6 papers · 1 filter
Physics-Informed Boundary Integral Networks (PIBI-Nets): A Data-Driven Approach for Solving Partial Differential Equations
Monika Nagy-Huber, Volker Roth
Partial differential equations (PDEs) are widely used to describe relevant phenomena in dynamical systems. In real-world applications, we commonly need to combine formal PDE models…
Lagrangian Flow Networks for Conservation Laws
F. Arend Torres, Marcello Massimo Negri, Marco Inversi +2
We introduce Lagrangian Flow Networks (LFlows) for modeling fluid densities and velocities continuously in space and time. By construction, the proposed LFlows satisfy the continui…
Mesh-free Eulerian Physics-Informed Neural Networks
Fabricio Arend Torres, Marcello Massimo Negri, Monika Nagy-Huber +2
Physics-informed Neural Networks (PINNs) have recently emerged as a principled way to include prior physical knowledge in form of partial differential equations (PDEs) into neural…
Learning Invariances with Generalised Input-Convex Neural Networks
Vitali Nesterov, Fabricio Arend Torres, Monika Nagy-Huber +2
Considering smooth mappings from input vectors to continuous targets, our goal is to characterise subspaces of the input domain, which are invariant under such mappings. Thus, we w…
Learning Conditional Invariance through Cycle Consistency
Maxim Samarin, Vitali Nesterov, Mario Wieser +3
Identifying meaningful and independent factors of variation in a dataset is a challenging learning task frequently addressed by means of deep latent variable models. This task can…
On the Empirical Neural Tangent Kernel of Standard Finite-Width Convolutional Neural Network Architectures
Maxim Samarin, Volker Roth, David Belius
The Neural Tangent Kernel (NTK) is an important milestone in the ongoing effort to build a theory for deep learning. Its prediction that sufficiently wide neural networks behave as…