67 citations · 375 across the 47 of their papers we have counts for
4 papers · 1 filter
Parallel Discrete Convolutions on Adaptive Particle Representations of Images
Joel Jonsson, Bevan L. Cheeseman, Suryanarayana Maddu +2
We present data structures and algorithms for native implementations of discrete convolution operators over Adaptive Particle Representations (APR) of images on parallel computer a…
Inverse-Dirichlet Weighting Enables Reliable Training of Physics Informed Neural Networks
Suryanarayana Maddu, Dominik Sturm, Christian L. Müller +1
We characterize and remedy a failure mode that may arise from multi-scale dynamics with scale imbalances during training of deep neural networks, such as Physics Informed Neural Ne…
A Mathematical Definition of Particle Methods
Johannes Bamme, Ivo F. Sbalzarini
We provide a formal definition for a class of algorithms known as "particle methods". Particle methods are used in scientific computing. They include popular simulation methods, su…
STENCIL-NET: Data-driven solution-adaptive discretization of partial differential equations
Suryanarayana Maddu, Dominik Sturm, Bevan L. Cheeseman +2
Numerical methods for approximately solving partial differential equations (PDE) are at the core of scientific computing. Often, this requires high-resolution or adaptive discretiz…