9 papers
Encoding the Euler Characteristic Transform
Nello Blaser, Odin Hoff Gardaa, Lars M. Salbu +2
The Euler Characteristic Curve (ECC) records the Euler characteristic of a linearly embedded cell complex as a function of filtration height in a given direction, and the Euler Cha…
No Triangulation Without Representation: Generalization in Topological Deep Learning
Johannes S. Schmidt, Martin Carrasco, Ernst Röell +3
Despite an ever-increasing interest in topological deep learning models that target higher-order datasets, there is no consensus on how to evaluate such models. This is exacerbated…
SO(3)-Equivariant Neural Networks for Learning from Scalar and Vector Fields on Spheres
Francesco Ballerin, Nello Blaser, Erlend Grong
Analyzing scalar and vector fields on the sphere, such as temperature or wind speed and direction on Earth, is a difficult task. Models should respect both the rotational symmetrie…
Calibrated and uncertain? Evaluating uncertainty estimates in binary classification models
Aurora Grefsrud, Nello Blaser, Trygve Buanes
Rigorous statistical methods, including parameter estimation with accompanying uncertainties, underpin the validity of scientific discovery, especially in the natural sciences. Wit…
Evaluating Prediction Uncertainty Estimates from BatchEnsemble
Morten Blørstad, Herman Jangsett Mostein, Nello Blaser +1
Deep learning models struggle with uncertainty estimation. Many approaches are either computationally infeasible or underestimate uncertainty. We investigate \textit{BatchEnsemble}…
Reeb Graph of Sample Thickenings
HÃ¥vard Bakke Bjerkevik, Nello Blaser, Lars M. Salbu
We consider the Reeb graph of a thickening of points sampled from an unknown space. Our main contribution is a framework to transfer reconstruction results similar to the well-know…