no code implementations • 15 Feb 2024 • Maria Bånkestad, Jennifer Andersson, Sebastian Mair, Jens Sjölund
Typically, the reduction approaches either remove edges (sparsification) or merge nodes (coarsening) in an unsupervised way with no specific downstream task in mind.
1 code implementation • 21 Nov 2023 • Maria Bånkestad, Keven M. Dorst, Göran Widmalm, Jerk Rönnols
Nuclear Magnetic Resonance (NMR) spectroscopy plays a crucial role in understanding their intricate molecular arrangements and is essential in assessing and verifying the molecular structure of organic molecules.
no code implementations • 21 Nov 2023 • Maria Bånkestad, Jens Sjölund, Jalil Taghia, Thomas B. Schöon
We present elliptical processes, a family of non-parametric probabilistic models that subsume Gaussian processes and Student's t processes.
no code implementations • 6 Jul 2022 • Johan Broberg, Maria Bånkestad, Erik Ylipää
Molecular property prediction is essential in chemistry, especially for drug discovery applications.
no code implementations • 1 Feb 2022 • Jens Sjölund, Maria Bånkestad
We describe a graph-based neural acceleration technique for nonnegative matrix factorization that builds upon a connection between matrices and bipartite graphs that is well-known in certain fields, e. g., sparse linear algebra, but has not yet been exploited to design graph neural networks for matrix computations.
no code implementations • 13 Mar 2020 • Maria Bånkestad, Jens Sjölund, Jalil Taghia, Thomas Schön
We present the elliptical processes -- a family of non-parametric probabilistic models that subsumes the Gaussian process and the Student-t process.
no code implementations • 25 Sep 2019 • Jalil Taghia, Maria Bånkestad, Fredrik Lindsten, Thomas Schön
Models that output a vector of responses given some inputs, in the form of a conditional mean vector, are at the core of machine learning.
no code implementations • 4 Feb 2019 • Jalil Taghia, Maria Bånkestad, Fredrik Lindsten, Thomas B. Schön
However, in certain scenarios we are interested in learning structured parameters (predictions) in the form of symmetric positive definite matrices.