ae-bii/neural-geometry
Latent Space Geometry for Neural Networks in Python
This library helps machine learning researchers and data scientists understand the complex, hidden structures within neural networks. It takes a trained neural network and applies geometric analysis techniques to reveal insights into how the network processes information. The output helps users interpret and optimize their models, particularly for tasks involving product manifold inference.
No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning researcher or data scientist looking to deeply understand and manipulate the internal, high-dimensional 'latent spaces' of your neural network models.
Not ideal if you are a practitioner solely focused on applying pre-built models or need a simple, high-level interpretation of network outputs.
Stars
19
Forks
1
Language
Python
License
MIT
Category
Last pushed
Jul 18, 2024
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ae-bii/neural-geometry"
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