activity
20192026
most citedConstructing the Matrix Multilayer Perceptron and its Application to the VAE

4 citations · 8 across the 4 of their papers we have counts for

collaborators

5 papers

cs.LG2026

Observation-dependent Bayesian active learning via input-warped Gaussian processes

Sanna Jarl, Maria Bånkestad, Jonathan J. S. Scragg +1

Bayesian active learning relies on the precise quantification of predictive uncertainty to explore unknown function landscapes. While Gaussian process surrogates are the standard f…

cs.LG20231 cited

Carbohydrate NMR chemical shift predictions using E(3) equivariant graph neural networks

Maria Bånkestad, Keven M. Dorst, Göran Widmalm +1

Carbohydrates, vital components of biological systems, are well-known for their structural diversity. Nuclear Magnetic Resonance (NMR) spectroscopy plays a crucial role in understa…

cs.LG20223 cited

Graph-based Neural Acceleration for Nonnegative Matrix Factorization

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…

stat.ME2020

The Elliptical Processes: a Family of Fat-tailed Stochastic Processes

Maria Bånkestad, Jens Sjölund, Jalil Taghia +1

We present the elliptical processes -- a family of non-parametric probabilistic models that subsumes the Gaussian process and the Student-t process. This generalization includes a…

stat.ML20194 cited

Constructing the Matrix Multilayer Perceptron and its Application to the VAE

Jalil Taghia, Maria Bånkestad, Fredrik Lindsten +1

Like most learning algorithms, the multilayer perceptrons (MLP) is designed to learn a vector of parameters from data. However, in certain scenarios we are interested in learning s…