srom/distributions

Notebooks on how to use PyTorch distributions to build probabilistic deep neural networks.

28
/ 100
Experimental

This project helps machine learning practitioners build models that can express their uncertainty about predictions. It takes your existing PyTorch models and data, and shows you how to integrate probabilistic layers. The result is a more robust model that can quantify its confidence, useful for applications where knowing 'how sure' the model is matters.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher using PyTorch and need your models to provide confidence intervals or uncertainty estimates alongside their predictions.

Not ideal if you are new to PyTorch or deep learning, or if you primarily work with non-neural network machine learning models.

Probabilistic Modeling Deep Learning Uncertainty Quantification Machine Learning Engineering AI Research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

10

Forks

4

Language

Jupyter Notebook

License

Last pushed

Jan 11, 2022

Commits (30d)

0

Get this data via API

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

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