39 citations · 61 across the 4 of their papers we have counts for
3 papers · 1 filter
Variational Data Assimilation with a Learned Inverse Observation Operator
Thomas Frerix, Dmitrii Kochkov, Jamie A. Smith +3
Variational data assimilation optimizes for an initial state of a dynamical system such that its evolution fits observational data. The physical model can subsequently be evolved i…
Homogeneous Linear Inequality Constraints for Neural Network Activations
Thomas Frerix, Matthias Nießner, Daniel Cremers
We propose a method to impose homogeneous linear inequality constraints of the form on neural network activations. The proposed method allows a data-driven training appr…
Proximal Backpropagation
Thomas Frerix, Thomas Möllenhoff, Michael Moeller +1
We propose proximal backpropagation (ProxProp) as a novel algorithm that takes implicit instead of explicit gradient steps to update the network parameters during neural network tr…