michael-psenka/manifold-linearization
Companion repository for the paper "Representation Learning via Manifold Flattening and Reconstruction"
This project helps machine learning engineers or researchers automatically design efficient autoencoders. You input your raw dataset, and it outputs a neural network autoencoder with optimized layer dimensions and training duration, specifically tailored to the geometric structure of your data. This is ideal for those working on representation learning tasks.
No commits in the last 6 months.
Use this if you need to build a neural network autoencoder and want to avoid the tedious trial-and-error process of guessing network architecture dimensions.
Not ideal if your dataset's underlying structure is not amenable to being approximated by a 'flattenable' manifold.
Stars
19
Forks
3
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jul 18, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/michael-psenka/manifold-linearization"
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