taspheres | R Documentation |
Creates a dataframe consisting of samples from the d-spheres of radius
r
enclosed within a larger d-sphere of radius 5 * r
.
taspheres(n_samples = 500, d = 100, n_spheres = 11, r = 5)
n_samples |
Number of points to sample from each of the |
d |
The dimensionality of each sphere. The returned dataframe will have
the |
n_spheres |
Number of spheres to return. There will be
|
r |
The radius of each of the smaller spheres. The larger sphere has
radius |
This dataset was used by Moor and co-workers in their "Topological Autoencoders" paper and this function is based on the Python code in the github repo for the paper.
Data frame with d + 1
numerical columns containing the
coordinates of the d-spheres and a "label"
factor column giving the
identity of each d-sphere: levels 0 .. n_spheres - 2
are the smaller
d-spheres. Level n_spheres - 1
is the label for the big d-sphere.
Moor, M., Horn, M., Rieck, B., & Borgwardt, K. (2020). Topological Autoencoders. In Proceedings of the 37th International Conference on Machine Learning (ICML) (pp. 7045–7054). PMLR.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.