Search Results for author:
Found 3 papers, 0 papers with code
Designing Rotationally Invariant Neural Networks from PDEs and Variational Methods
With only a few small filters, they can achieve the same invariance as existing techniques which require a fine-grained sampling of orientations.
Connections between Numerical Algorithms for PDEs and Neural Networks
We connect these concepts to residual networks, recurrent neural networks, and U-net architectures.
Sparse Inpainting with Smoothed Particle Hydrodynamics
Furthermore, we examine the use of Voronoi tessellation for defining the necessary parameters in the SPH method as well as selecting optimally located image samples.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
