brian-hepler-phd/Spherical-CNN
Interactive exploration of equivariant neural networks on homogeneous spaces, with a focus on the sphere S² as SO(3)/SO(2). From Lecture 8 of the Lie groups course with Quantum Formalism
This Jupyter notebook helps researchers and advanced students understand how to build neural networks that respect the natural symmetries of 3D data, like spheres. It takes complex mathematical concepts from Lie group theory and demonstrates how they apply to creating deep learning models for spherical data. The output is a clear, interactive visualization of how these 'equivariant' networks operate, making abstract ideas tangible for those working with spherical or 3D geometric datasets.
No commits in the last 6 months.
Use this if you are a researcher or advanced student in fields like climate science, astrophysics, molecular modeling, or 3D computer vision, and you need to understand the theoretical foundations and practical implementation of neural networks for data on spheres.
Not ideal if you are looking for a plug-and-play solution for general deep learning tasks without a strong interest in the underlying geometric deep learning principles or if you don't work with data exhibiting rotational symmetries.
Stars
16
Forks
2
Language
Jupyter Notebook
License
—
Category
Last pushed
May 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/brian-hepler-phd/Spherical-CNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lmcinnes/umap
Uniform Manifold Approximation and Projection
pyRiemann/pyRiemann
Machine learning for multivariate data through the Riemannian geometry of positive definite...
geomstats/geomstats
Computations and statistics on manifolds with geometric structures.
higra/Higra
Hierarchical Graph Analysis
pavlin-policar/openTSNE
Extensible, parallel implementations of t-SNE