3 citations · 3 across the 9 of their papers we have counts for
10 papers
Atom-JEPA: Joint-Embedding Predictive Architecture for 3D Atomistic Systems
Kasper Helverskov Petersen, Rasmus Hannibal Tirsgaard, François R J Cornet +2
Large-scale self-supervised pretraining has reshaped modern machine learning, substantially advancing the ability of language and vision models to generalize across downstream task…
Semi-Supervised Learning for Molecular Graphs via Ensemble Consensus
Rasmus Tirsgaard, Laurits Fredsgaard, Marisa Wodrich +2
Machine learning is transforming molecular sciences by accelerating property prediction, simulation, and the discovery of new molecules and materials. Acquiring labeled data in the…
Equivariant Graph Neural Networks Improve Optical Spectra Prediction for Materials Screening
Kasper Helverskov Petersen, François R J Cornet, Martin Ovesen +3
Scalable prediction of optical spectra is a critical component of high-throughput materials screening for optoelectronic applications such as solar cells. Existing surrogate models…
Practical Deep Heteroskedastic Regression
Mikkel Jordahn, Jonas Vestergaard Jensen, James Harrison +2
Uncertainty quantification (UQ) in deep learning regression is of wide interest, as it supports critical applications including sequential decision making and risk-sensitive tasks.…
On Local Posterior Structure in Deep Ensembles
Mikkel Jordahn, Jonas Vestergaard Jensen, Mikkel N. Schmidt +1
Bayesian Neural Networks (BNNs) often improve model calibration and predictive uncertainty quantification compared to point estimators such as maximum-a-posteriori (MAP). Similarly…
Bayesian Optimization via Continual Variational Last Layer Training
Paul Brunzema, Mikkel Jordahn, John Willes +3
Gaussian Processes (GPs) are widely seen as the state-of-the-art surrogate models for Bayesian optimization (BO) due to their ability to model uncertainty and their performance on…
Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks
Mikkel Jordahn, Pablo M. Olmos
Deep Neural Networks (DNN) have shown great promise in many classification applications, yet are widely known to have poorly calibrated predictions when they are over-parametrized.…
Neural machine translation for automated feedback on children's early-stage writing
Jonas Vestergaard Jensen, Mikkel Jordahn, Michael Riis Andersen
In this work, we address the problem of assessing and constructing feedback for early-stage writing automatically using machine learning. Early-stage writing is typically vastly di…
On the role of Model Uncertainties in Bayesian Optimization
Jonathan Foldager, Mikkel Jordahn, Lars Kai Hansen +1
Bayesian optimization (BO) is a popular method for black-box optimization, which relies on uncertainty as part of its decision-making process when deciding which experiment to perf…
Topic Model Robustness to Automatic Speech Recognition Errors in Podcast Transcripts
Raluca Alexandra Fetic, Mikkel Jordahn, Lucas Chaves Lima +4
For a multilingual podcast streaming service, it is critical to be able to deliver relevant content to all users independent of language. Podcast content relevance is conventionall…