no code implementations • NeurIPS Workshop DLDE 2021 • Ben Moseley, Andrew Markham, Tarje Nissen-Meyer
Recently, physics-informed neural networks (PINNs) have offered a powerful new paradigm for solving forward and inverse problems relating to differential equations.
1 code implementation • 16 Jul 2021 • Ben Moseley, Andrew Markham, Tarje Nissen-Meyer
FBINNs are designed to address the spectral bias of neural networks by using separate input normalisation over each subdomain, and reduce the complexity of the underlying optimisation problem by using many smaller neural networks in a parallel divide-and-conquer approach.
no code implementations • CVPR 2021 • Ben Moseley, Valentin Bickel, Ignacio G. Lopez-Francos, Loveneesh Rana
Recently, learning-based approaches have achieved impressive results in the field of low-light image denoising.
no code implementations • 11 Oct 2019 • Ryan Curtin, Ben Moseley, Hung Q. Ngo, XuanLong Nguyen, Dan Olteanu, Maximilian Schleich
When the data matrix needs to be obtained from a relational database via a feature extraction query, the computation cost can be prohibitive, as the data matrix may be (much) larger than the total input relation size.
no code implementations • 26 May 2019 • Ryan R. Curtin, Sungjin Im, Ben Moseley, Kirk Pruhs, Alireza Samadian
Our main result is that if the regularizer's effect does not become negligible as the norm of the hypothesis scales, and as the data scales, then a uniform sample of modest size is with high probability a coreset.