Tensorflow implementation of Hyperspherical Variational Auto-Encoders
-
Updated
Dec 1, 2018 - Python
Tensorflow implementation of Hyperspherical Variational Auto-Encoders
Code for EMNLP18 paper "Spherical Latent Spaces for Stable Variational Autoencoders"
Directional Co-clustering with a Conscience (DCC)
Pytorch implementation of Hyperspherical Variational Auto-Encoders
Kernel density estimation on a sphere
Spherical statistics in Python
Sampling from the von Mises - Fisher distribution
Fit and manipulate a few probability distribution functions on the unit S2 sphere.
This is the repository for the research project about the Generalized Procrustes Analysis using spatial anatomical information in fMRI data, i.e., the ProMises (Procrustes von Mises-Fisher) model
The following includes all the MATLAB scripts necessary for implementing the algorithm described in the attached paper.
Clustering routines for the unit sphere
Fast Generation of von Mises-Fisher Distributed Pseudo-Random Vectors
spherical clustering, von-Mises Fisher mixture model
Add a description, image, and links to the von-mises-fisher topic page so that developers can more easily learn about it.
To associate your repository with the von-mises-fisher topic, visit your repo's landing page and select "manage topics."