EdoardoBotta/Gaussian-Mixture-VAE

[Pytorch] Minimal implementation of a Variational Autoencoder (VAE) with Categorical Latent variables inspired from "Categorical Reparameterization with Gumbel-Softmax".

26
/ 100
Experimental

This project helps machine learning engineers and researchers analyze complex time-series data. It takes in sequential data, such as sensor readings or financial prices, and identifies underlying, distinct patterns or 'modes' that govern how the data evolves over time. The output is a model that can explain these hidden patterns and potentially generate new data following the same rules.

No commits in the last 6 months.

Use this if you need to identify and model discrete, switching behaviors within continuous time-series data, where the exact 'state' influencing the data's evolution is not directly observed.

Not ideal if your data does not have a sequential, time-dependent nature or if you need a model that explicitly handles continuous latent variables.

time-series-analysis unsupervised-learning pattern-discovery data-generation anomaly-detection
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

7

Forks

3

Language

Python

License

Last pushed

Jun 16, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/EdoardoBotta/Gaussian-Mixture-VAE"

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