timsainb/ParametricUMAP_paper

Parametric UMAP embeddings for representation and semisupervised learning. From the paper "Parametric UMAP: learning embeddings with deep neural networks for representation and semi-supervised learning" (Sainburg, McInnes, Gentner, 2020).

39
/ 100
Emerging

This project provides the original code for Parametric UMAP, a method to learn efficient data representations. It takes in high-dimensional datasets and outputs a lower-dimensional embedding that captures the structure and relationships within the data. Data scientists, machine learning engineers, and researchers can use this to improve semi-supervised learning tasks.

152 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer who needs a highly customizable implementation of Parametric UMAP to integrate into your deep neural network models or reproduce specific research results.

Not ideal if you're looking for the standard, user-friendly implementation of Parametric UMAP; in that case, you should use the main UMAP library (v0.5+).

machine-learning-research deep-learning data-representation semi-supervised-learning dimensionality-reduction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

152

Forks

15

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 08, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/timsainb/ParametricUMAP_paper"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.