IParraMartin/Sparse-Autoencoder

A PyTorch implementation of a Sparse Auto Encoder (SAE) using MSE loss and KL Divergence penalty

19
/ 100
Experimental

This project provides an easy-to-understand implementation of a sparse autoencoder, a type of neural network that learns to represent data efficiently. It takes in raw data, like images, and learns a compressed, meaningful representation. This tool is designed for students or researchers who want to learn how these models work under the hood.

No commits in the last 6 months.

Use this if you are a student or researcher looking for an educational, from-scratch implementation of a sparse autoencoder to understand its core mechanics.

Not ideal if you need a high-performance or production-ready solution for data compression or feature extraction.

machine-learning-education neural-networks data-compression feature-learning
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

27

Forks

1

Language

Python

License

Last pushed

Sep 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/IParraMartin/Sparse-Autoencoder"

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