Machine learning

Scalable and Equivariant Spherical CNNs by Discrete-Continuous (DISCO) Convolutions
No existing spherical convolutional neural network (CNN) framework is both computationally scalable and rotationally equivariant. …
PDF Cite Code arXiv
Bayesian model comparison for simulation-based inference
Comparison of appropriate models to describe observational data is a fundamental task of science. The Bayesian model evidence, or …
PDF Cite Code arXiv
harmonic: Learnt harmonic mean estimator for Bayesian model selection
A professional grade Python implementation of the learnt harmonic mean estimator (McEwen et al. 2021).
Dec 10, 2021
PDF GitHub PyPi Docs arXiv
harmonic: Learnt harmonic mean estimator for Bayesian model selection
Machine learning assisted Bayesian model comparison: learnt harmonic mean estimator
We resurrect the infamous harmonic mean estimator for computing the marginal likelihood (Bayesian evidence) and solve its problematic …
PDF Cite Code arXiv
Efficient generalized spherical CNNs
Many problems across computer vision and the natural sciences require the analysis of spherical data, for which representations may be …
PDF Cite Code arXiv