no code implementations • 20 Dec 2023 • Rafael Orozco, Philipp Witte, Mathias Louboutin, Ali Siahkoohi, Gabrio Rizzuti, Bas Peters, Felix J. Herrmann
InvertibleNetworks. jl is a Julia package designed for the scalable implementation of normalizing flows, a method for density estimation and sampling in high-dimensional distributions.
no code implementations • 9 Feb 2023 • Bas Peters
We introduce CQnet, a neural network with origins in the CQ algorithm for solving convex split-feasibility problems and forward-backward splitting.
no code implementations • 27 Jul 2020 • Bas Peters
We illustrate the capabilities in case of a) one or more classes do not have any annotation; b) there is no annotation at all; c) there are bounding boxes.
no code implementations • 17 Mar 2020 • Bas Peters
We show that explicit regularization of model parameters in PDE constrained optimization translates to regularization of the network output.
no code implementations • 16 Mar 2020 • Bas Peters, Eldad Haber, Keegan Lensink
The large spatial/frequency scale of hyperspectral and airborne magnetic and gravitational data causes memory issues when using convolutional neural networks for (sub-) surface characterization.
no code implementations • 14 Dec 2019 • Bas Peters, Eldad Haber, Keegan Lensink
Factors that limit the size of the input and output of a neural network include memory requirements for the network states/activations to compute gradients, as well as memory for the convolutional kernels or other weights.
no code implementations • 24 May 2019 • Keegan Lensink, Bas Peters, Eldad Haber
However, their application to problems with high dimensional input and output, such as high-resolution image and video segmentation or 3D medical imaging, has been limited by various factors.
no code implementations • 27 Mar 2019 • Bas Peters, Eldad Haber, Justin Granek
Neural-networks have seen a surge of interest for the interpretation of seismic images during the last few years.
no code implementations • 12 Jan 2019 • Bas Peters, Justin Granek, Eldad Haber
Tests on seismic images and interpretation information from the Sea of Ireland show that we obtain high-quality predicted interpretations from a small number of large seismic images.
no code implementations • 26 Dec 2018 • Bas Peters, Justin Granek, Eldad Haber
Our networks learn from a small number of large seismic images without creating patches.