cod3licious/simec

Similarity Encoder (SimEc) Neural Network Framework for learning low dimensional similarity preserving representations

31
/ 100
Emerging

This project helps researchers analyze complex datasets by transforming raw feature vectors into a lower-dimensional representation that preserves specific similarities between data points. You input your raw data and a defined similarity metric, and it outputs a compressed, meaningful representation of your data. This is ideal for machine learning researchers or data scientists exploring new ways to understand relationships in their data.

No commits in the last 6 months.

Use this if you need to create compact, similarity-preserving representations from high-dimensional data, especially when traditional methods struggle with noise or non-linear relationships.

Not ideal if you're looking for an out-of-the-box solution for common data analysis tasks without delving into neural network architectures or if you need a non-research-grade, production-ready system.

data-embedding dimensionality-reduction machine-learning-research recommender-systems link-prediction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

17

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 28, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/cod3licious/simec"

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