Tue Boesen

Neural DAEs: Constrained Neural Networks

Tue Boesen, Eldad Haber, Uri M. Ascher

Abstract. This article investigates the effect of explicitly adding auxiliary algebraic trajectory information to neural networks for dynamical systems. We draw inspiration from the field of differential algebraic equations and differential equations on manifolds and implement related methods in residual neural networks, …

ca (code pays fourni par la source)

32 Water molecule simulation

Tue Boesen

This is a microcanonical ensemble (NVE) simulation of 32 water molecules at a temperature of 300 K, approximated with the Lennard-Jones force-field, using cp2k. The physical simulation is done employing a step-size of 0.1 fs for 100,000 steps. The simulation is done …

ca (code pays fourni par la source)

32 Water molecule simulation

Tue Boesen

This is a microcanonical ensemble (NVE) simulation of 32 water molecules at a temperature of 300 K, approximated with the Lennard-Jones force-field, using cp2k. The physical simulation is done employing a step-size of 0.1 fs for 100,000 steps. The simulation is done …

ca (code pays fourni par la source)

A-optimal active learning

Tue Boesen, Eldad Haber

Abstract In this work we discuss the problem of active learning. We present an approach that is based on A-optimal experimental design of ill-posed problems and show how one can optimally label a data set by partially probing it, and use it …

ca (code pays fourni par la source)

Neural DAEs: Constrained neural networks

Tue Boesen, Eldad Haber, Uri M. Ascher

This article investigates the effect of explicitly adding auxiliary algebraic trajectory information to neural networks for dynamical systems. We draw inspiration from the field of differential-algebraic equations and differential equations on manifolds and implement related methods in residual neural networks, despite some …

Mimetic Neural Networks: A Unified Framework for Protein Design and Folding

Moshe Eliasof, Tue Boesen, Eldad Haber, Chen Keasar et autres

Recent advancements in machine learning techniques for protein structure prediction motivate better results in its inverse problem-protein design. In this work we introduce a new graph mimetic neural network, MimNet, and show that it is possible to build a reversible architecture that …

il, ca (code pays fourni par la source)

A-Optimal Active Learning

Tue Boesen, Eldad Haber

In this work we discuss the problem of active learning. We present an approach that is based on A-optimal experimental design of ill-posed problems and show how one can optimally label a data set by partially probing it, and use it to …

Mimetic Neural Networks: A unified framework for Protein Design and Folding

Moshe Eliasof, Tue Boesen, Eldad Haber, Chen Keasar et autres

Recent advancements in machine learning techniques for protein folding motivate better results in its inverse problem -- protein design. In this work we introduce a new graph mimetic neural network, MimNet, and show that it is possible to build a reversible architecture …

Data-driven semi-supervised clustering for oil prediction

Tue Boesen, Eldad Haber, G. Michael Hoversten

ca, us (code pays fourni par la source)

An efficient 2D inversion scheme for airborne frequency-domain data

Tue Boesen, Esben Auken, Anders Vest Christiansen, Gianluca Fiandaca et autres

ABSTRACT In many cases, inversion in 2D gives a better description of the subsurface compared with 1D inversion, but, computationally, 2D inversion is expensive, and it can be hard to use for large-scale surveys. We have developed an efficient hybrid 2D airborne …

dk, no (code pays fourni par la source)

A parallel computing thin‐sheet inversion algorithm for airborne time‐domain data utilising a variable overburden

Tue Boesen, Esben Auken, Anders Vest Christiansen, Gianluca Fiandaca et autres

ABSTRACT Accurate modelling of the conductivity structure of mineralisations can often be difficult. In order to remedy this, a parametric approach is often used. We have developed a parametric thin‐sheet code, with a variable overburden. The code is capable of performing inversions …

dk, fr (code pays fourni par la source)

Numerical methods for electromagnetic geophysics beyond 1D

Tue Boesen

dk (code pays fourni par la source)