aleximmer/Laplace

Laplace approximations for Deep Learning.

49
/ 100
Emerging

This project helps machine learning practitioners incorporate uncertainty directly into their deep learning models. By applying Laplace approximations to neural networks, it takes your trained model and training data to provide a refined model that can quantify its own prediction confidence. This is useful for data scientists, ML engineers, and researchers working with deep learning models.

535 stars. No commits in the last 6 months.

Use this if you need to understand the confidence or uncertainty in your deep learning model's predictions, rather than just getting a single output.

Not ideal if you're looking for a fully automated, 'set it and forget it' solution, as optimal results require experimentation with different configuration options.

predictive-uncertainty model-confidence bayesian-deep-learning deep-learning-research model-selection
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

535

Forks

89

Language

Python

License

MIT

Last pushed

Apr 22, 2025

Commits (30d)

0

Get this data via API

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

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